AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Models

Gemini 3.8 Flash (Medium)

September 2, 2026Last synced Nov 5, 2026, 12:17 AM
Effort
  • Low
  • Medium
  • High

Blended Price

$1.50/M

Input Price

$0.75/M

Output Price

$3.75/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index
30.1
Coding Index
—
Math Index
—
MMLU Pro
— / 100
GPQA Diamond
93.5 / 100
HLE
42.1 / 100
LiveCodeBench
— / 100
SciCode
55.1 / 100
MATH-500
— / 100
AIME
— / 30
AIME 2025
— / 30
IFBench
— / 100
LCR
84.0 / 100
Terminal-Bench Hard
— / 100
τ²-Bench
— / 100

Performance Radar

Gemini 3.8 Flash (Medium)
Field Average

Hidden, no data: AgMoBench Overall, AgMoBench Coding, AgMoBench Math, AgMoBench Agentic, AgMoBench Robustness, Output Speed

* Shared benchmarks shown in their place: GPQA Diamond, HLE, SciCode

External Benchmarks

ARC-AGI-1arc_agi
97.5 / 100
ARC-AGI-1 Cost per Taskarc_agi
0.1
ARC-AGI-2arc_agi
82.9 / 100
ARC-AGI-2 Cost per Taskarc_agi
0.2
Arc Agi 2epoch_ai
0.8
Critptepoch_ai
0.1
Cursorbenchepoch_ai
0.4
DeepSWE (Epoch Import, Version Unverified)epoch_ai
0.7 / 100
Dtbenchepoch_ai
0.9
Frontiercodeepoch_ai
0.4
Gdp Pdfepoch_ai
0.2
Lmcaepoch_ai
52.9
Scicodeepoch_ai
0.6
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-20

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-20

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-20

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-20

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-18

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-18

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-17

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-17

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-16

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-16

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-10

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-10

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-09

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-09

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-06

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-06

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-04

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-04

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-02

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-02

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-28

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-28

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-21

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-21

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-19

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-19

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-15

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-15

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-14

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-14

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-14

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-14

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-13

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-13

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-06

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-06

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-02

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-02

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-01

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-01

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"8bfe2e142f29acec39df406a6631f81a\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"92bfaa47028eae49163960f4c5a298a0\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-30

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"8bfe2e142f29acec39df406a6631f81a\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"92bfaa47028eae49163960f4c5a298a0\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-30

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"16793624264c3bdded076b4e26af5a90\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"e7fb37556a7353e7da435c4c7b78ca50\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-29

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"16793624264c3bdded076b4e26af5a90\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"e7fb37556a7353e7da435c4c7b78ca50\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-29

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"284ac3aff89a7d8a3aca179ee1e5dd61\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"6e0849a05a2c572b1050e5900a372e2b\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-28

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"284ac3aff89a7d8a3aca179ee1e5dd61\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"6e0849a05a2c572b1050e5900a372e2b\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-28

24.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the standard harness.",
  "modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 2727.66378825,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-24

4.0 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Gemini 3.8 Flash - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:google-gemini-3-8-flash-medium-provider-adapter

View run source

Source metadata
{
  "provider": "Google",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "google-gemini-3-8-flash-provider-adapter",
  "modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness.",
  "modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
  "upstreamModelId": "google-gemini-3-8-flash-medium-provider-adapter",
  "environmentCount": 25,
  "modelReleaseDate": "2026-09-02T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 3826.20432375,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-24

24.2 / 100

How Gemini 3.8 Flash (Medium) Compares

Axes

Filters

$0.00 – $67.5
≥ 1.4

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu
openai
zai
meta
nvidia
xai
upstage
deepseek
alibaba
mistral
nous-research
aws
google
anthropic
xiaomi
stepfun
kimi
reflection
minimax
azure
inclusionai
reka-ai
cohere
bytedance_seed
inception
tencent
thinking-machines
Bubble size = Context Window
8191.00
2000000.00
Compare with other models