Benchmarks / AutomationBench AutomationBench leaderboard As of November 14, 2026, among the results listed here, DeepSeek V4.1 Flash has the highest reported AutomationBench score, 54.8% (Pass@1), published by DeepSeek, ahead of Google Gemini 4 Carbon at 53.9%. 20 models have a AutomationBench result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Share Cite Cite this page: LLMBenchmark.ai, "AutomationBench Leaderboard: Scores Reported by AI Labs (November 2026)", https://llmbenchmark.ai/benchmarks/automationbench, accessed November 14, 2026 .
Copy citation Best reported score
54.8%
DeepSeek V4.1 Flash
Reported by DeepSeek, September 10, 2026 · Pass@1
20 models ranked · 8 makers
Reported AutomationBench scores AutomationBench scores reported by model makers Rank Model Score Setting Reported by Date 1 DeepSeek V4.1 Flash 54.8% Pass@1 DeepSeek September 10, 2026 (model release) 2 Gemini 4 Carbon 53.9% Zapier Google October 28, 2026 · read from the maker's chart 3 Claude Fable 5.2 51.4% Not published Anthropic November 9, 2026 (model release) 4 Gemini 4 Argon 51.3% Score Google October 13, 2026 (model release) 5 GLM 5.3 Flash 48.8% Not published Z.ai August 26, 2026 (model release) · read from the maker's chart 6 Claude Opus 5.5 42.5% Not published Anthropic November 9, 2026 (model release) 7 Claude Fable 5.1 31.4% Not published Anthropic May 27, 2026 (model release) · read from the maker's chart 8 Kimi K3 30.8% max Moonshot AI July 16, 2026 (model release) 9 Gemini 3.7 Flash 30.4% Private set Google August 13, 2026 (model release) 10 LFM2.5-24B-A2B 27.7% Not published Liquid October 13, 2026 (model release) 11 Qwen3.8 Max (0902) 27.3% Pass@1 Qwen August 3, 2026 12 Claude Opus 5 26.9% Not published Anthropic May 27, 2026 (model release) · read from the maker's chart 13 GLM 5.2 26.2% Not published Z.ai August 26, 2026 (model release) · read from the maker's chart 14 GPT-5.6 Sol 18.1% Not published OpenAI August 7, 2025 (model release) 15 Claude Fable 5 17.1% Not published Anthropic June 9, 2026 (model release) 16 Gemini 3.6 Flash 17.0% Private set Google August 13, 2026 (model release) 17 GPT-5.6 Terra 15.2% Not published OpenAI August 7, 2025 (model release) 18 GPT-5.6 Luna 14.9% Not published OpenAI August 7, 2025 (model release) 19 Qwen3.7 Max 14.2% Pass@1 Qwen August 3, 2026 20 GPT-5.5 12.9% Not published OpenAI August 7, 2025 (model release)
Other reported runs How much to trust these numbers
Source Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
Settings Settings differ between makers. Check the Setting column before comparing two scores.
Spread 54.8% to 12.9% across 20 models.
Freshness Newest result published November 9, 2026; oldest August 7, 2025.
Charts Some values were read from charts in the announcements. Two independent readings had to match exactly. What AutomationBench measures AutomationBench scores how well AI agents complete realistic business workflows across applications using REST APIs. Source: zapier/AutomationBench
