Back to models
Intelligence Index
Reasoning setting
10.8#71 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.25 in / $0.80 out / 1M tokOpenRouter · Arcee AI
- Context window
- 512K tok
Performance profile
ReasoningRank #66 of 107
75.2%
GPQA DiamondCodingRank #61 of 94
40.6%
SciCodeCost efficiencyRank #29 of 67
91.1pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)Trinity Large Thinking
Cost per task (USD) · log scale
Trinity Large ThinkingReasoning
- Intelligence Index
- 10.8
- Cost / task
- $0.1188
- Evaluation time
- 2.1m
Pricing & access
USD per 1M tokens
- Input
- $0.25
- Output
- $0.80
- Cached input
- $0.06
Run locally
- Original download
- 797.3 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)15.8%, rank 75 of 12640.6%, rank 61 of 940.5%, rank 46 of 8738.0%, rank 98 of 125337 Elo, rank 86 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 72G9v3-39A5BReasoning17.5%
- 73HyperNova 60B 2605High16.6%
- 74KAT Coder Pro V2Standard16.1%
- 75Trinity Large ThinkingReasoning15.8%
- 76Gemma 4 12BReasoning15.7%
- 77Qwen3.5 9BReasoning14.9%
- 78Qwen3.5 Omni PlusStandard14.9%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherLing 3.0 TinyReasoning
- Intelligence Index
- 11.1+0.2
- Higher score, lower costGPT-6 LunaMax
- Intelligence Index
- 38.1+27.3
- Cost / task
- $0.068−43%
- Similar scoreGranite 4.2 8BReasoning
- Intelligence Index
- 11.1+0.3
- Cost / task
- $0.024−80%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.