Benchmark
Terminal-Bench 2.0
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 60
- Scores recorded
- 60
- Sources
- 3
- IQ weight
- 1.98
Score distribution
- 49.4%
- Mean
- 49.4%
- Median
- 14.7%
- Std dev
- 30%
- 10th percentile
- 69%
- 90th percentile
- 22.5%
- Min
This benchmark has a weight of 1.98 for chat models, measured over 60 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.7% |
| 2 | Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.4% |
| 3 | GPT-5.3 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.3% |
| 4 | Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.2% |
| 5 | GPT 5.4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.1% |
| 6 | Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.6% |
| 7 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.3% |
| 8 | Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.7% |
| 9 | Claude Opus 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.4% |
| 10 | GLM 5.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 69% |
| 11 | Gemini 3.1 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.5% |
| 12 | MiMo V2.5 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 68.4% |
| 13 | DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.9% |
| 14 | Kimi K2.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 66.7% |
| 15 | MiMo V2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 65.8% |
| 16 | Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 65.4% |
| 17 | GPT-5.2 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 64% |
| 18 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.6% |
| 19 | GPT-5.4 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60% |
| 20 | Claude Opus 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.3% |
| 21 | Qwen3.6 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 59.3% |
| 22 | Claude Sonnet 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.1% |
| 23 | Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59% |
| 24 | MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.1% |
| 25 | MiniMax M2.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 57% |
| 26 | DeepSeek V4 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 56.9% |
| 27 | GLM 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 56.2% |
| 28 | Hy3 (Deep Infra)· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.4% |
| 29 | Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.2% |
| 30 | GPT-5.1 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.8% |
| 31 | Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 52.5% |
| 32 | Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 51.5% |
| 33 | Step 3.5 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 51% |
| 34 | Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 50.8% |
| 35 | Qwen3.5 122B-A10B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 49.4% |
| 36 | Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 47.6% |
| 37 | DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.4% |
| 38 | DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 46.4% |
| 39 | DeepSeek V3.2 Speciale· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.4% |
| 40 | GPT 5.4 Nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.3% |
| 41 | Mai Thinking 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46% |
| 42 | Laguna M.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.8% |
| 43 | Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.2% |
| 44 | Qwen3.5 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 41.6% |
| 45 | GLM 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 41% |
| 46 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 40.5% |
| 47 | ling-2.6-1t· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 40.5% |
| 48 | MiMo V2 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 38.5% |
| 49 | Laguna XS 2.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 37.5% |
| 50 | Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 37.5% |
Showing 1–50 of 60 results.
Data credits: Data by LLM Stats · OpenEvals/leaderboard-data, MIT (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark