EpiBench (Research Workflows): leaderboard

EpiBench (2026, research workflows) is an episodic benchmark in which multimodal agents search the literature, extract evidence from figures and tables across papers and reuse it over several turns to answer research questions. This board is the episode success rate in percent, the share of episodes with every turn answered correctly; higher is better.

Metric: Episode success rate (%): share of episodes with every turn answered correctly, over the 102 EpiBench episodes (39 easy, 63 hard), each a multi-turn research workflow in which the agent searches papers, extracts figures and tables with tools and answers objective questions, the final turn from stored evidence only; answers judged by GPT-5.2; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.239.6#185
2Kimi K2.535.35#266
3GPT-5 Mini24.51#364
4Gemini 2.5 Pro14.71#276
5Qwen 3 VL 235B A22B (Thinking)13.73#459
6Qwen 3 VL 235B A22B Instruct12.75#532
7Grok 4.19.8#462
8GLM-4.5V2.94#754

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

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