Benchmark
AutomationBench v1.0.6
Scores are percentages. Higher is better.
- Models measured
- 17
- Scores recorded
- 18
- Sources
- 2
- IQ weight
- 0.10
Score distribution
- 47.8%
- Mean
- 49.7%
- Median
- 10.3%
- Std dev
- 36.1%
- 10th percentile
- 60.5%
- 90th percentile
- 20.7%
- Min
This benchmark has a weight of 0.10 for chat models, measured over 17 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 | MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.8% |
| 2 | MiniMax M3.1 FlashMiniMax M3.1 Flash official-weights model-card run · reasoning effort, sampling, and run count not stated for this benchmark · v1.0.6 · 600 publicly released tasks· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.8% |
| 3 | DeepSeek V4.1 Flash 1017DeepSeek 1017 first-party evaluation · reasoning effort, candidate sampling, exact run count, and unspecified harnesses not published · published main score · metric subtype and harness unspecified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.5% |
| 4 | MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.1% |
| 5 | GPT-6.2 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.4% |
| 6 | MiMo V2.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.3% |
| 7 | Hy4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.2% |
| 8 | LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.8% |
| 9 | Qwen3.8 MaxAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.7% |
| 10 | Claude Opus 5Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.4% |
| 11 | GLM 5.3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.2% |
| 12 | Kimi K3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 45.9% |
| 13 | GPT-5.6 SolAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 45.7% |
| 14 | DeepSeek V4 Pro 0813Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41.7% |
| 15 | GPT-6.2 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.2% |
| 16 | GPT-6.1 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 36.1% |
| 17 | GPT-6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 33.2% |
| 18 | GPT-6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 20.7% |
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