OccuBench - Agriculture & Environment: leaderboard

Metric: Completion rate (%) on the Agriculture & Environment 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 January 2027. 15 models tracked.

Top models

#ModelScore
1GPT-5.2 (High)84
2Qwen 3.5 Plus (Thinking)77
3Claude Opus 4.6 (High)74
4Gemini 3.1 Pro (Preview)68
5Kimi K2.5 (Thinking)68
6Claude Sonnet 4.5 (Thinking)65
7DeepSeek V3.2 (Thinking)65
8Qwen 3.5 Flash (Thinking)61
9Claude Opus 4.5 (Thinking)58
10Claude Sonnet 4.6 (Thinking)58
11GLM-5 (Thinking)55
12Claude Opus 4 (Thinking)52
13MiniMax-M2.748
14Claude Sonnet 4 (Thinking)35

Interactive version: theaggregate.ai/benchmark?slug=occubench-agriculture-environment · How It Works · Data refreshed daily, snapshot 2026-10-07.