FeynmanBench - Vertex Inventory: leaderboard

Metric: CP1 pass rate (%), count and type of every interaction vertex with its linked fields, checked by rule-based scripts, on FeynmanBench's Feynman-diagram tasks (a rendered diagram plus minimal conventions; Standard Model QED, electroweak and QCD diagrams from tree level to two loops), API models at temperature 0, mean of five runs; four models ran on subsets of 165 to 742 items, the others on about 2,000; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 19 models tracked.

Top models

#ModelScore
1Gemini 3 Flash94.7
2Gemini 3.1 Pro (Preview)85.7
3Seed 2.0 Pro79.1
4Qwen 3.6 Plus72.6
5Qwen 3.5 Plus66.7
6Claude Sonnet 4.665.2
7GLM-5V Turbo57.4
8GPT-5.146.7
9GPT-5.446.3
10GPT-5.239.9
11Claude Opus 4.538.6
12Claude Opus 4.632.6
13Claude Opus 4.731.4
14Kimi K2.511.2
15Claude Sonnet 4.56.5

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