Back to models
Intelligence Index
Reasoning setting
19.1#53 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.12 in / $0.48 out / 1M tokOpenRouter · AtlasCloud · FP8 · promotional
- Context window
- 1M tok
Performance profile
ReasoningRank #57 of 107
78.0%
GPQA DiamondCodingRank #75 of 94
36.3%
SciCodeCost efficiencyRank #12 of 67
324.0pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)LongCat 2.0
Cost per task (USD) · log scale
LongCat 2.0Reasoning
- Intelligence Index
- 19.1
- Cost / task
- $0.059
Pricing & access
USD per 1M tokens
- Input
- $0.12
- Output
- $0.48
- Cached input
- $0.0024
Run locally
- Original download
- 3,551.7 GB
- App memory
- Unverified
- Documented software
- SGLangSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)33.7%, rank 43 of 12636.3%, rank 75 of 940.0%, rank 56 of 8765.0%, rank 73 of 125856 Elo, rank 58 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 40Apodex 1.1Reasoning34.1%
- 41Qwen3.8-27BExtra high33.9%
- 42Nex-N2-ProReasoning33.7%
- 43LongCat 2.0Reasoning33.7%
- 44Agnes 2.5 Pro AlphaReasoning33.6%
- 45Hy3Reasoning33.5%
- 46Inkling SmallReasoning33.3%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherK2 Horizon 7BReasoning
- Intelligence Index
- 20.6+1.5
- Lower cost, close scoreMistral Small 4Reasoning
- Intelligence Index
- 11.3−7.8
- Cost / task
- $0.015−74%
- Similar scoreQwen3.5 397B A17BReasoning
- Intelligence Index
- 18.4−0.7
- Cost / task
- $0.475+705%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.