IUMB — leaderboard
16 introductory undergraduate math problems across topology, number theory, geometry, group theory, probability, real analysis, and combinatorics. Models tested with 3 attempts each (5 for avg@5 variants).
Metric: Score (%). Source: pellaml.github.io. Status: saturated. 55 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | GPT-5.5 Pro | 100 |
| 3 | GPT-5.4 Pro (xHigh) | 97.9 |
| 4 | GPT-5.2 Pro | 89.6 |
| 5 | Gemini 3 Deep Think | 87.5 |
| 6 | Gemini 3.1 Pro (Preview) | 85.4 |
| 7 | GPT-5.4 (Thinking) | 81.2 |
| 8 | Claude Opus 4.6 (Thinking) | 79.2 |
| 9 | GPT-5.2 (High) | 77.1 |
| 10 | GPT-5.2 (xHigh) | 68.8 |
| 11 | Muse Spark | 66.7 |
| 12 | Gemini 3 Pro (Preview) | 62.5 |
| 13 | DeepSeek V3.2 Speciale | 62.5 |
| 14 | GLM-4.7 | 58.3 |
| 15 | Step 3.5 Flash | 58.3 |
Interactive version: theaggregate.ai/benchmark?slug=iumb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.