Blended Price
$0.20/M
Input Price
$0.100/M
Output Price
$0.50/M
Speed
—
TTFT
—
Not enough shared data to draw a radar
This model has 1 of the selected dimensions; a radar needs 3.
Missing: AgMoBench Overall, AgMoBench Reasoning, AgMoBench Coding, AgMoBench Math, AgMoBench Agentic, AgMoBench Robustness, Output Speed
Axes
Filters
Providers
v3 · public-demo · GPT-6 Luna - Provider Adapter (None) · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-none-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'none' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "openai-gpt-6-luna-none-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 205.03171590000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · GPT-6 Luna - Provider Adapter (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-max-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'max' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "openai-gpt-6-luna-max-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 237.1428722,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · GPT-6 Luna - Provider Adapter (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-high-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'high' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "openai-gpt-6-luna-high-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 223.89528660000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · GPT-6 Luna - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-medium-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "openai-gpt-6-luna-medium-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 213.71995940000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · GPT-6 Luna - Provider Adapter (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-low-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'low' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "openai-gpt-6-luna-low-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 214.29109010000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · GPT-6 Luna - Provider Adapter (XHigh) · effort xhigh · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-xhigh-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'xhigh' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "openai-gpt-6-luna-xhigh-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 223.17200050000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · GPT-6 Luna - Provider Adapter (None) · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-none-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'none' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "openai-gpt-6-luna-none-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 205.03171590000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-high-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'high' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "openai-gpt-6-luna-high-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 223.89528660000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-low-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'low' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "openai-gpt-6-luna-low-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 214.29109010000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (XHigh) · effort xhigh · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-xhigh-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'xhigh' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "openai-gpt-6-luna-xhigh-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 223.17200050000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-max-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'max' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "openai-gpt-6-luna-max-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 237.1428722,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-medium-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "openai-gpt-6-luna-medium-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 213.71995940000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-max-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'max' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "openai-gpt-6-luna-max-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 237.1428722,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-high-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'high' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "openai-gpt-6-luna-high-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 223.89528660000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-medium-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'medium' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "openai-gpt-6-luna-medium-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 213.71995940000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-low-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'low' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "openai-gpt-6-luna-low-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 214.29109010000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (None) · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-none-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'none' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "openai-gpt-6-luna-none-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 205.03171590000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · GPT-6 Luna - Provider Adapter (XHigh) · effort xhigh · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-6-luna-xhigh-provider-adapter
{
"provider": "OpenAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "openai-gpt-6-luna-provider-adapter",
"modelNotes": "Evaluation conducted with 'xhigh' reasoning effort using the provider adapter harness. Some model actions have unmeasured token usage; reported costs are recorded-usage lower bounds, not verified full-run costs.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "openai-gpt-6-luna-xhigh-provider-adapter",
"environmentCount": 25,
"modelReleaseDate": "2026-09-22T00:00:00.000Z",
"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": 223.17200050000002,
"providerModelIdPublished": false
}Evidence observed 2026-09-22