Benchmark
Terminal-Bench
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 61
- Scores recorded
- 67
- Sources
- 3
- IQ weight
- 1.73
Score distribution
- 41.8%
- Mean
- 39.5%
- Median
- 18.5%
- Std dev
- 21.8%
- 10th percentile
- 66.5%
- 90th percentile
- 3.4%
- Min
This benchmark has a weight of 1.73 for chat models, measured over 61 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 |
|---|---|---|
| 51 | MiMo V2 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.5% |
| 52 | GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30% |
| 53 | Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 30% |
| 54 | Grok 4· Epoch AI Benchmarking Hub data | 27.2% |
| 55 | Qwen3 Coder· Epoch AI Benchmarking Hub data | 27.2% |
| 56 | Grok Code Fast 1· Epoch AI Benchmarking Hub data | 25.8% |
| 57 | Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.8% |
| 58 | Qwen3.6 35B A3B· Epoch AI Benchmarking Hub data | 24.6% |
| 59 | GPT-5 nano· Epoch AI Benchmarking Hub data | 21.8% |
| 60 | GPT OSS 120B· Epoch AI Benchmarking Hub data | 18.7% |
| 61 | gemini-2.5-flash-preview-09-2025· Epoch AI Benchmarking Hub data | 17.1% |
| 62 | Gemini 2.5 Flash· Epoch AI Benchmarking Hub data | 17.1% |
| 63 | GPT-5 nanomedium· Epoch AI Benchmarking Hub data | 11.5% |
| 64 | Qwen3.5 9B· Epoch AI Benchmarking Hub data | 9.2% |
| 65 | Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 8.5% |
| 66 | DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 5.7% |
| 67 | GPT OSS 20b· Epoch AI Benchmarking Hub data | 3.4% |
Showing 51–67 of 67 results.
Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark