Benchmark
AutomationBench
Scores are percentages. Higher is better.
- Models and systems measured
- 41
- Scores recorded
- 152
- Sources
- 2
- IQ weight
- 0.00
Score distribution
- 29.8%
- Mean
- 30.3%
- Median
- 13.5%
- Std dev
- 13.5%
- 10th percentile
- 48.8%
- 90th percentile
- 1.2%
- Min
This benchmark has a weight of 0.00 for chat models, measured over 39 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 51 | GPT-6.1 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · high reasoning · displayed cost $0.23/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.2% |
| 52 | GPT-6 Solxhigh effort · $0.2746 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.2% |
| 53 | Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 32.1% |
| 54 | Hy4 previewv1.0.6· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32.1% |
| 55 | GPT-6 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · max reasoning · displayed cost $0.34/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32% |
| 56 | GPT-6 Solmax effort · $0.3406 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32% |
| 57 | DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.8% |
| 58 | DeepSeek V4 Pro 0813public subset · pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.8% |
| 59 | GPT-6.1 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · medium reasoning · displayed cost $0.19/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.7% |
| 60 | Claude Fable 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.4% |
| 61 | Claude Fable 5.1Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.4% |
| 62 | Claude Fable 5.1OpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.4% |
| 63 | Claude Fable 5.1Opus 5.5 System Card · adaptive thinking · max effort unless stated · v1.0.6 leaderboard · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.4% |
| 64 | Claude Fable 5.1System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.4% |
| 65 | GPT-6 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · high reasoning · displayed cost $0.24/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.2% |
| 66 | GPT-6 Solhigh effort · $0.2368 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.2% |
| 67 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.8% |
| 68 | Kimi K3600-task public subset · max effort · temp 1.0 · top_p 1.0· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30.8% |
| 69 | Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.4% |
| 70 | Gemini 3.7 Flashprivate set· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30.4% |
| 71 | GPT-6 AstraAutomationBench v1.0.6 · 47 tools · OpenAI release chart · low reasoning · displayed cost $1.08/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30.3% |
| 72 | GPT-6 Astralow effort · $1.08 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30.3% |
| 73 | GPT-5.6 SolQwen表:600题公开子集 · Pass@1· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.7% |
| 74 | Claude Fable 5Qwen表:600题公开子集 · Pass@1· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.1% |
| 75 | GPT-5.6 Solmax effort · $0.67 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.8% |
| 76 | Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 27.3% |
| 77 | Qwen3.8 MaxQwen表:600题公开子集 · Pass@1· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 27.3% |
| 78 | Claude Opus 4.8Qwen表:600题公开子集 · Pass@1· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 27.2% |
| 79 | GPT-6 Solmedium effort · $0.2098 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 80 | Claude Opus 5Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 81 | Claude Opus 5max effort · $3.05 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 82 | Claude Opus 5OpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 83 | Claude Opus 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · v1.0.6 leaderboard · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 84 | Claude Opus 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 85 | GPT-6 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · medium reasoning · displayed cost $0.21/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.9% |
| 86 | GPT-5.6 Solxhigh effort · $0.54 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 87 | Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26% |
| 88 | Claude Opus 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26% |
| 89 | DeepSeek V4 Flash Vision Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.7% |
| 90 | Claude Opus 5xhigh effort · $2.71 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.3% |
| 91 | DeepSeek V4 Flash 0731· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.1% |
| 92 | DeepSeek V4 Flash 0731public subset· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.1% |
| 93 | GPT-5.6 Solhigh effort · $0.47 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.8% |
| 94 | GPT-6.1 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · low reasoning · displayed cost $0.16/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.7% |
| 95 | Claude Opus 5medium effort · $2.22 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 23.9% |
| 96 | GPT-6 SolAutomationBench v1.0.6 · 47 tools · OpenAI release chart · low reasoning · displayed cost $0.19/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 21.2% |
| 97 | GPT-6 Sollow effort · $0.1861 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 21.2% |
| 98 | GPT-6 Lunamax effort · $0.0367 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.7% |
| 99 | Claude Opus 5high effort · $2.27 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.5% |
| 100 | Claude Opus 5low effort · $1.64 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.4% |
Showing 51–100 of 145 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Claude Fable 5.1 with Opus 5 fallbackAutomationBench v1.0.6 · 47 tools · OpenAI release chart · max reasoning · displayed cost $2.45/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.4% |
| Claude Fable 5.1 with Opus 5 fallbackmax effort · $2.45 average cost/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.4% |
| Claude Opus 5.5 with fallbacks (OpenAI chart label)AutomationBench v1.0.6 · 47 tools · OpenAI release chart · high reasoning · displayed cost $0.71/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33% |
| Claude Opus 5.5 with fallbacks (OpenAI chart label)AutomationBench v1.0.6 · 47 tools · OpenAI release chart · low reasoning · displayed cost $0.51/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.2% |
| Claude Opus 5.5 with fallbacks (OpenAI chart label)AutomationBench v1.0.6 · 47 tools · OpenAI release chart · max reasoning · displayed cost $1.44/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 42.5% |
| Claude Opus 5.5 with fallbacks (OpenAI chart label)AutomationBench v1.0.6 · 47 tools · OpenAI release chart · medium reasoning · displayed cost $0.65/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.5% |
| Claude Opus 5.5 with fallbacks (OpenAI chart label)AutomationBench v1.0.6 · 47 tools · OpenAI release chart · xhigh reasoning · displayed cost $0.89/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 35.8% |
Data credits: Data by LLM Stats · 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.