Back to models
Intelligence Index
Reasoning setting
43.7#14 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 1M tok
Performance profile
CodingRank #11 of 94
58.9%
SciCodeCost efficiencyRank #41 of 67
42.6pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)Step 5 Preview
Cost per task (USD)
Step 5 PreviewReasoning
- Intelligence Index
- 43.7
- Cost / task
- $1.03
- Evaluation time
- 9.9m
Pricing & access
No API offering listed in our tracked sources.
Benchmarks
Full leaderboardSource (opens in a new tab)46.5%, rank 14 of 12658.9%, rank 11 of 9433.3%, rank 13 of 8788.3%, rank 2 of 1251,587 Elo, rank 20 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 11Gemini 3.8 FlashHigh47.8%
- 12Gemini 3.1 Pro PreviewReasoning47.0%
- 13Kimi-K3Max46.9%
- 14Step 5 PreviewReasoning46.5%
- 15Claude Haiku 5.5Max44.4%
- 16Muse Spark OpenExtra high43.9%
- 17JT-4.1 Flash 236B A21BReasoning43.6%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherGLM-5.3Max
- Intelligence Index
- 44.8+1.0
- Cost / task
- $2.01+95%
- Higher score, lower costMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+2.6
- Cost / task
- $0.133−87%
- Similar scoreKimi-K3Max
- Intelligence Index
- 43.6−0.1
- Cost / task
- $2.00+95%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.