OccuBench - Healthcare & Life Sciences: 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 Healthcare & Life Sciences tasks in the clean environment, in percent; higher is better.

Metric: Completion rate (%) on the Healthcare & Life Sciences 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: Not forecast. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Kimi K2.5Thinking81#266
2Qwen 3.5 PlusThinking81#242
3GPT-5.2High76#185
4Claude Opus 4.6High76#113
5Qwen 3.5 FlashThinking76#441
6Claude Sonnet 4.5Thinking71#261
7DeepSeek V3.2Thinking71#419
8Claude Sonnet 4.6Thinking67#173
9Gemini 3.1 Flash LiteThinking67#371
10Gemini 3.1 Pro (Preview)62#99
11MiniMax-M2.757#539
12Claude Sonnet 4Thinking57#410
13GLM-5Thinking57#269
14Claude Opus 4Thinking57#326
15Claude Opus 4.5Thinking52#160

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

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