BlueFin - Public Set: leaderboard

Metric: Criteria-weighted rubric score (%; points met over maximum points of expert rubrics checked by an agentic GPT-5.4 judge for synthesis and manipulation workbooks, answer correctness for interrogation, non-completions count as zero; 20-tool spreadsheet harness, high reasoning effort; micro-average over the 11 released tasks: 7 manipulation, 1 synthesis, 3 interrogation). Source: arxiv.org. Saturation forecast: Around June 2027. 7 models tracked.

Top models

#ModelScore
1Claude Opus 4.7 (High)58.4
2GPT-5.5 (High)54.1
3Claude Sonnet 4.6 (High)48.7
4Gemini 3.1 Pro (Preview) (High)46.8
5Kimi K2.642.3
6MiniMax-M2.520.9

Interactive version: theaggregate.ai/benchmark?slug=bluefin-public-set · How It Works · Data refreshed daily, snapshot 2026-09-26.