IOLBench - Short Answer: leaderboard
Metric: Accuracy (%; string match, 666 text problems). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 61.12 |
| 2 | Claude Opus 4 | 41.9 |
| 3 | Gemini 2.5 Pro | 39.76 |
| 4 | Grok 4 | 38.11 |
| 5 | Claude Sonnet 4 | 36.84 |
| 6 | GPT-4o | 26.87 |
| 7 | GPT-4 | 24.48 |
| 8 | GPT-4o Mini | 20.62 |
| 9 | Gemini 2.5 Flash | 19.76 |
Interactive version: theaggregate.ai/benchmark?slug=iolbench-short-answer · How It Works · Data refreshed daily, snapshot 2026-09-24.