OccuBench - Technology & IT: leaderboard

Metric: Completion rate (%) on the Technology & IT 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)80
2Gemini 3.1 Pro (Preview)78
3DeepSeek V3.2 (Thinking)74
4Kimi K2.5 (Thinking)74
5Qwen 3.5 Plus (Thinking)74
6GLM-5 (Thinking)70
7Claude Sonnet 4.5 (Thinking)68
8Claude Opus 4.5 (Thinking)68
9Claude Opus 4.6 (High)68
10Claude Opus 4 (Thinking)66
11MiniMax-M2.764
12Claude Sonnet 4.6 (Thinking)64
13Claude Sonnet 4 (Thinking)60
14Qwen 3.5 Flash (Thinking)60

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