MathArena - Project Euler 971-984: leaderboard
Project Euler computational math problems 971-984, separating a later question group so scores compare models on problems they were actually tested on.
Metric: Accuracy (%, direct Project Euler problems 971-984). Source: matharena.ai. Saturation forecast: Around January 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (High) | 92.86 | #63 (Claude Opus 4.6) |
| 2 | GPT-5.4 (xHigh) | 91.07 | #79 (GPT-5.4) |
| 3 | Gemini 3.1 Pro (Preview) | 89.29 | #58 |
| 4 | Gemini 3.5 Flash | 82.14 | #60 |
| 5 | GPT-5.2 (High) | 82.14 | #110 (GPT-5.2) |
| 6 | GLM-5.1 | 61.31 | #97 |
| 7 | Gemini 3 Flash | 55.36 | #99 |
| 8 | Kimi K2.5 (Thinking) | 51.79 | #144 (Kimi K2.5) |
| 9 | Gemini 3 Pro (Preview) | 50 | #66 |
| 10 | DeepSeek V3.2 (Thinking) | 50 | #205 (DeepSeek V3.2) |
| 11 | Grok 4.1 Fast (Reasoning) | 35.71 | #217 (Grok 4.1 Fast) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=matharena-project-euler-971-984 · How It Works · Data refreshed daily, snapshot 2026-10-20.