Benchmark
Agents' Last Exam · Pass Rate
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 16
- Scores recorded
- 23
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 26.7%
- Mean
- 27%
- Median
- 4.4%
- Std dev
- 22.8%
- 10th percentile
- 31.8%
- 90th percentile
- 11.8%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017DeepSeek 1017 first-party evaluation · reasoning effort, candidate sampling, exact run count, and unspecified harnesses not published · published pass rate · harness unspecified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 35.4% |
| 2 | 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. | 31.8% |
| 3 | DeepSeek V4.1 Flash官方 scaffold / Pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.8% |
| 4 | GPT-5.6 SolQwen表:Pass Rate· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30.6% |
| 5 | 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. | 28.6% |
| 6 | GLM 5.3ALE-CLI / Pass@1· Reported by Z.ai, DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.5% |
| 7 | 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. | 28.5% |
| 8 | Kimi K3Kimi Code · official leaderboard snapshot 2026-07-23· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.3% |
| 9 | Kimi K3ALE-CLI / Pass@1· Reported by Z.ai, DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 27.6% |
| 10 | 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. | 27.6% |
| 11 | Claude Opus 4.8Qwen表:Pass Rate· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 27% |
| 12 | Qwen3.8 MaxQwen表:Pass Rate· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 27% |
| 13 | 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. | 26.7% |
| 14 | Gemini 3.7 FlashALE-Claw· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 15 | GLM 5.3 Flashofficial ALE · Claude Code max · 1M · 64K output · Tool Search disabled· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 16 | 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. | 25.7% |
| 17 | DeepSeek V4 Pro 0813official scaffold · pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.7% |
| 18 | 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. | 25.2% |
| 19 | DeepSeek V4 Flash 0731multimodal inputs explicitly ignored· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.2% |
| 20 | Qwen 3.8 Flash NextQwen3.8-Flash-Next release/model card · Pass@1· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.3% |
| 21 | Hy4 previewCLI· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 22.8% |
| 22 | Qwen 3.8 27BQwen3.8-27B model card · Pass@1· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.4% |
| 23 | Qwen3.7 MaxQwen表:Pass Rate· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 11.8% |