Back to models
Intelligence Index
Reasoning setting
30.5#32 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 524.29K tok
Performance profile
ReasoningRank #29 of 107
87.3%
GPQA DiamondCodingRank #54 of 94
42.9%
SciCodeCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)Pricing & access
No API offering listed in our tracked sources.
Run locally
- Original download
- 758.3 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)32.0%, rank 47 of 12642.9%, rank 54 of 941.5%, rank 38 of 8780.0%, rank 31 of 1251,349 Elo, rank 32 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 44Agnes 2.5 Pro AlphaReasoning33.6%
- 45Hy3Reasoning33.5%
- 46Inkling SmallReasoning33.3%
- 47K2 Horizon 375B A23BReasoning32.0%
- 48InklingExtra high31.9%
- 49Nemotron 3.5 Super VLReasoning30.7%
- 50A.X-K2Reasoning29.6%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherQwen3.8-27BExtra high
- Intelligence Index
- 33.7+3.2
- Cost / task
- $1.01
- More from Institute of Foundation ModelsK2 Horizon MoVA 36B A4BReasoning
- Intelligence Index
- 25.3−5.2
- Similar scoreBeam 1.0Reasoning
- Intelligence Index
- 30.3−0.2
- Cost / task
- $0.566
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.