Back to models
Intelligence Index
Reasoning setting
33.9#30 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 256K tok
Performance profile
CodingRank #26 of 94
52.0%
SciCodeCapabilities
Context window
Modalities
Measured settings
Reasoning trade-offs
Source (opens in a new tab)| Mode | Intelligence Index |
|---|---|
| StandardEstimated | 27.3 |
| Reasoning | 33.9 |
Pricing & access
No API offering listed in our tracked sources.
Benchmarks
Full leaderboardSource (opens in a new tab)43.6%, rank 17 of 12652.0%, rank 26 of 943.0%, rank 34 of 8778.3%, rank 41 of 1251,316 Elo, rank 34 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 14Step 5 PreviewReasoning46.5%
- 15Claude Haiku 5.5Max44.4%
- 16Muse Spark OpenExtra high43.9%
- 17JT-4.1 Flash 236B A21BReasoning43.6%
- 18Grok 4.7Extra high43.1%
- 19Qwen3.8 Max (0902)Reasoning43.1%
- 20GPT-5.6 TerraMax42.9%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higher
- Intelligence Index
- 34.8+0.9
- Cost / task
- $0.314
- Similar scoreQwen3.8-27BExtra high
- Intelligence Index
- 33.7−0.2
- Cost / task
- $1.01
- Similar score
- Intelligence Index
- 36.0+2.1
- Cost / task
- $0.674
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.