Benchmark
Terminal-Bench 2.0 · Harness Unspecified
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 56.2%
- Mean
- 57.1%
- Median
- 9.8%
- Std dev
- 46.3%
- 10th percentile
- 65.8%
- 90th percentile
- 38.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | MiMo V2.5 ProXiaomi MiMo-V2.5-Pro official launch table · version 2.0 · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.4% |
| 2 | MiMo V2.5Xiaomi MiMo-V2.5 official release/model card · version 2.0 · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.8% |
| 3 | GPT-5.4 minixhigh · publisher did not name the harness· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60% |
| 4 | MiMo V2 ProXiaomi MiMo-V2-Pro release table · version 2.0 · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.1% |
| 5 | MiniMax M2.7MiniMax M2.7 official release prose · Terminal Bench 2 · harness unspecified· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57% |
| 6 | GPT 5.4 Nanoxhigh · publisher did not name the harness· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 46.3% |
| 7 | MiMo V2 FlashMiMo-V2-Flash final evaluation · version 2.0 · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 38.5% |