OccuBench - Education & Culture: leaderboard

OccuBench (2026) evaluates agents on 382 professional tool-use tasks from 100 occupational scenarios in 10 industries, against environments simulated by Gemini-3-Flash-Preview, each trajectory passed or failed by a rubric verifier; thinking mode on, high effort where configurable. This board is the completion rate on the Education & Culture tasks in the clean environment, in percent; higher is better.

Metric: Completion rate (%) on the Education & Culture industry's tasks in the clean environment (E0); 382 tool-use task instances from 100 professional scenarios, the environment simulated by Gemini-3-Flash-Preview and each trajectory passed or failed by a rubric verifier; thinking mode on, high reasoning effort where configurable; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)84#99
2GPT-5.2High77#185
3Claude Opus 4.6High75#113
4Claude Sonnet 4.6Thinking69#173
5DeepSeek V3.2Thinking66#419
6Kimi K2.5Thinking62#266
7Claude Opus 4.5Thinking62#160
8Qwen 3.5 PlusThinking56#242
9GLM-5Thinking53#269
10Claude Opus 4Thinking53#326
11Qwen 3.5 FlashThinking53#441
12Gemini 3.1 Flash LiteThinking53#371
13Claude Sonnet 4.5Thinking50#261
14Claude Sonnet 4Thinking38#410
15MiniMax-M2.731#539

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=occubench-education-culture · How It Works · Data refreshed daily, snapshot 2026-11-21.