Back to models
Intelligence Index
Reasoning setting
20.6#52 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 524.29K tok
Performance profile
ReasoningRank #64 of 107
75.3%
GPQA DiamondCodingRank #83 of 94
27.5%
SciCodeCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)Reasoning
- Intelligence Index
- 20.6
Pricing & access
No API offering listed in our tracked sources.
Run locally
- Original download
- 18 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)18.2%, rank 71 of 12627.5%, rank 83 of 941.0%, rank 39 of 8769.7%, rank 66 of 1251,023 Elo, rank 50 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 68Gemini 3.5 Flash-LiteHigh18.8%
- 69Quasar 438BMax18.7%
- 70K-EXAONE 2.0 0803Reasoning18.6%
- 71K2 Horizon 7BReasoning18.2%
- 72G9v3-39A5BReasoning17.5%
- 73HyperNova 60B 2605High16.6%
- 74KAT Coder Pro V2Standard16.1%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherNemotron 3.5 Bolt 74B-A9BReasoning
- Intelligence Index
- 21.4+0.8
- More from Institute of Foundation ModelsK2 Horizon MoVA 36B A4BReasoning
- Intelligence Index
- 25.3+4.7
- Similar scoreA.X-K2Reasoning
- Intelligence Index
- 21.5+0.9
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.