IG-Bench - IG-Exam - Evolutionary Reasoning: leaderboard

Metric: Exact accuracy (%) on the 409 evolutionary-reasoning instances (17 task types) of IG-Exam. Source: arxiv.org. Saturation forecast: Around 2030. 12 models tracked.

Top models

#ModelScore
1GPT-5.523.3
2Kimi K2 (Thinking)19.6
3Qwen 3.6 Max Preview18.8
4DeepSeek V4 Pro18.6
5Gemini 3.1 Pro (Preview)17.8
6GLM-5.117.4
7Claude Opus 4.717.1
8MiniMax-M2.710.9

Interactive version: theaggregate.ai/benchmark?slug=ig-bench-ig-exam-evolutionary-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.