Back to models
Intelligence Index
Reasoning setting
3.0#83 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 131.07K tok
Performance profile
ReasoningRank #106 of 107
29.3%
GPQA DiamondCodingRank #94 of 94
6.9%
SciCodeCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)Reasoning
- Intelligence Index
- 3.0
Pricing & access
No API offering listed in our tracked sources.
Run locally
- Original download
- 2.2 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)5.4%, rank 106 of 1266.9%, rank 94 of 940.0%, rank 56 of 876.3%, rank 119 of 125-409 Elo, rank 101 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 104Llama 3.2 Instruct 11B (Vision)Standard5.5%
- 105NVIDIA Nemotron Nano 12B v2 VLReasoning5.5%
- 106Ministral 3 3BStandard5.4%
- 106K2 Horizon 0.9BReasoning5.4%
- 108Tiny Aya GlobalStandard5.2%
- 109Granite 4.0 MicroStandard5.0%
- 110Phi-4 Multimodal InstructStandard5.0%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherMinistral 3 3BStandard
- Intelligence Index
- 4.8+1.8
- Cost / task
- $0.008
- More from Institute of Foundation ModelsK2 Horizon 3.7BReasoning
- Intelligence Index
- 15.6+12.6
- Similar scoreMinistral 3 8BStandard
- Intelligence Index
- 5.5+2.4
- Cost / task
- $0.011
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.