ReliableMath - Precision — leaderboard
Metric: Score (%). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 | 64.2 |
| 2 | Qwen 3 235B A22B | 62.1 |
| 3 | doubao-seed-1.6-thinking-250615 | 59.4 |
| 4 | Qwen 3 14B | 57.3 |
| 5 | DeepSeek R1 0528 | 56.9 |
| 6 | DeepSeek R1 Distill Qwen 32B | 55.1 |
| 7 | DeepSeek R1 Distill Qwen 14B | 54.7 |
| 8 | Qwen 3 32B | 54.5 |
| 9 | DeepSeek V3 | 52.1 |
| 10 | Claude Sonnet 4 (Thinking) | 52 |
| 11 | Gemini 2.5 Flash (Preview 04-17) | 51.8 |
| 12 | Gemini 2.5 Flash (Preview 04-17) (Thinking) | 50.8 |
| 13 | O3 Mini (2025-01-31) | 50.4 |
| 14 | Claude Sonnet 4 (20250514) | 47.3 |
| 15 | GPT-4o (2024-08-06) | 39.7 |
Interactive version: aibenchmarks.dev/benchmark?slug=reliablemath-precision · How the rankings work · Data refreshed daily, snapshot 2026-07-08.