Benchmark
Terminal-Bench 3.0
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 10
- Scores recorded
- 21
- Sources
- 2
- IQ weight
- No weight published
Score distribution
- 25.8%
- Mean
- 28.3%
- Median
- 9.5%
- Std dev
- 14.9%
- 10th percentile
- 34.6%
- 90th percentile
- 7.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5DeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 43.3% |
| 2 | Claude Opus 5DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 43.3% |
| 3 | GPT-5.6 Solsetting not named by the source· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34.6% |
| 4 | GPT-5.6 SolDeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34.4% |
| 5 | GPT-5.6 SolDeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34.4% |
| 6 | DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30% |
| 7 | DeepSeek V4.1 FlashDeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30% |
| 8 | DeepSeek V4.1 FlashDeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30% |
| 9 | GLM 5.3setting not named by the source· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.3% |
| 10 | GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 28.3% |
| 11 | GLM 5.3DeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.3% |
| 12 | GLM 5.3DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.3% |
| 13 | Grok 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26% |
| 14 | Claude Opus 4.8· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 21.1% |
| 15 | Kimi K3DeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 17.7% |
| 16 | Kimi K3DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 17.7% |
| 17 | Kimi K3setting not named by the source· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 17.4% |
| 18 | Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 14.9% |
| 19 | Gemini 3.7 Flashmini-swe-agent · highest thinking· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 14.9% |
| 20 | DeepSeek V4 Pro 0813DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 11.8% |
| 21 | DeepSeek V4 Flash 0731DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 7.6% |
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats