AgMoDB
ModelsAgentsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Benchmarks

Arc Agi 2

Arc Agi 2 benchmark scores from Epoch AI's benchmark data collection.

aggregatePartial metadataepoch_ai

This definition has not completed editorial and provenance review. Verify its metric, version, source, and evaluation configuration upstream before using it for a model-selection decision.

Strengths

Sourced from Epoch AI's systematic benchmark data collection covering frontier models.

Caveats

Auto-generated definition — editorial description not yet written.

How to interpret scores

Contamination risk: moderateFreshness: periodic

Higher is better.

Caveat to keep in mind

Auto-generated definition — editorial description not yet written.

Leaderboard

Last synced: Nov 9, 2026, 4:18 PM
#ModelProviderScorePrice/M
1
Gemma 3 270M
source benchpress
Evidence observed Apr 13, 2026
Google100.0$0.00
2
Qwen3.5 0.8B (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Alibaba99.9$0.00
3
Llama 2 Chat 7B
source benchpress
Evidence observed Apr 13, 2026
Meta99.2$0.00
4
Reka Edge
source benchpress
Evidence observed Apr 13, 2026
Rekaai60.1$0.10
5
Reka Edge
source benchpress
Evidence observed Apr 13, 2026
Reka60.1$0.20
6
PALM-2
source benchpress
Evidence observed Apr 13, 2026
Google60.0$0.00
7
Reka Flash (Sep '24)
source benchpress
Evidence observed Apr 13, 2026
Reka AI20.5$0.35
8
Qwen2.5 72B Instruct
source benchpress
Evidence observed Apr 13, 2026
Alibaba19.4$0.19
9
Hermes 3 - Llama-3.1 70B
source benchpress
Evidence observed Apr 13, 2026
Nous Research15.3$0.70
10
Hermes 4 - Llama-3.1 70B (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
Nous Research9.4$0.00
11
Hermes 4 - Llama-3.1 70B (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Nous Research9.4$0.00
12
Sao10K: Llama 3.1 70B Hanami x1
source benchpress
Evidence observed Apr 13, 2026
Sao10k9.4$3.00
13
Mistral: Ministral 3 3B 2512
source benchpress
Evidence observed Apr 13, 2026
Mistral AI9.1$0.10
14
QwQ 32B
source benchpress
Evidence observed Apr 13, 2026
Alibaba6.3$0.00
15
Gemma 3 1B Instruct
source benchpress
Evidence observed Apr 13, 2026
Google5.7$0.00
16
WizardLM-2 8x22B
source benchpress
Evidence observed Apr 13, 2026
Microsoft5.2$0.62
17
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
Nous Research5.1$0.00
18
DeepSeek LLM 67B Chat (V1)
source benchpress
Evidence observed Apr 13, 2026
DeepSeek4.6$0.00
19
Meta: Llama 3.1 70B Instruct
source benchpress
Evidence observed Apr 13, 2026
Meta4.3$0.40
20
AlfredPros: CodeLLaMa 7B Instruct Solidity
source benchpress
Evidence observed Apr 13, 2026
Alfredpros3.9$0.90
21
Granite 4.0 350M
source benchpress
Evidence observed Apr 13, 2026
IBM3.8$0.00
22
Mistral: Ministral 3 8B 2512
source benchpress
Evidence observed Apr 13, 2026
Mistral AI3.7$0.15
23
Mixtral 8x22B Instruct
source benchpress
Evidence observed Apr 13, 2026
Mistral AI3.4$0.00
24
Qwen2.5 Instruct 72B
source benchpress
Evidence observed Apr 13, 2026
Alibaba2.7$0.48
25
LFM2.5-1.2B-Instruct
source benchpress
Evidence observed Apr 13, 2026
Liquid AI2.6$0.00
26
Google: Gemma 2 27B
source benchpress
Evidence observed Apr 13, 2026
Google2.2$0.65
27
Qwen3.5 0.8B (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
Alibaba2.1$0.00
28
Qwen2.5 Coder 32B Instruct
source benchpress
Evidence observed Apr 13, 2026
Alibaba2.1$0.05
29
Qwen2.5 Coder Instruct 32B
source benchpress
Evidence observed Apr 13, 2026
Alibaba2.1$0.00
30
o1
source benchpress
Evidence observed Apr 13, 2026
OpenAI1.7$26.25
31
Ministral 3 3B
source benchpress
Evidence observed Apr 13, 2026
Mistral AI1.6$0.10
32
Mistral: Ministral 3 14B 2512
source benchpress
Evidence observed Apr 13, 2026
Mistral AI1.5$0.20
33
Llama 2 Chat 70B
source benchpress
Evidence observed Apr 13, 2026
Meta1.5$0.00
34
Google: Gemma 2 9B
source benchpress
Evidence observed Apr 13, 2026
Google1.4$0.04
35
Meta: Llama 3.3 70B Instruct (free)
source benchpress
Evidence observed Apr 13, 2026
Meta1.4$0.00
36
Meta: Llama 3.3 70B Instruct
source benchpress
Evidence observed Apr 13, 2026
Meta1.4$0.15
37
Meta: Llama 3.2 1B Instruct
source benchpress
Evidence observed Apr 13, 2026
Meta1.2$0.07
38
Claude Sonnet 4.6 (Non-reasoning, High)
source benchpress
Evidence observed Apr 13, 2026
Anthropic1.2$6.00
39
LFM2 1.2B
source benchpress
Evidence observed Apr 13, 2026
Liquid AI1.0$0.00
40
GPT-6.1 Sol (Max)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$4.00
41
Claude Opus 5.5 (High, Default Fallback)
source epoch_ai
Evidence observed Nov 9, 2026
Anthropic0.9$8.00
42
GPT-6 Astra (Xhigh)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$20.00
43
GPT-5.6 Sol (Max)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$8.00
44
Claude Opus 5.5 (Xhigh, Default Fallback)
source epoch_ai
Evidence observed Nov 9, 2026
Anthropic0.9$8.00
45
GPT-6 Astra (Medium)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$20.00
46
GPT-6 Astra (High)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$20.00
47
Claude Opus 5.5
source epoch_ai
Evidence observed Nov 9, 2026
Anthropic0.9$8.00
48
GPT-6.1 Sol (Xhigh)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$4.00
49
GPT-6.1 Sol (High)
source epoch_ai
Evidence observed Nov 9, 2026
OpenAI0.9$4.00
50
Gemini 4 Argon (High)
source epoch_ai
Evidence observed Nov 9, 2026
Google0.9$8.00