xDailyBench - Quantitative Reasoning: leaderboard
Metric: Score (%). Source: arxiv.org. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3 | 72.6 |
| 2 | GPT-5.5 | 65.8 |
| 3 | GPT-5.6 Sol | 62.6 |
| 4 | Claude Opus 4.7 | 62.2 |
| 5 | Qwen 3.7 Max | 61.1 |
| 6 | DeepSeek V4 Pro | 59.6 |
| 7 | GLM-5.1 | 55.9 |
| 8 | Qwen 3.6 Max | 55.7 |
| 9 | Kimi K2.6 | 49.5 |
| 10 | Gemini 3.1 Pro (Preview) | 41.5 |
Interactive version: theaggregate.ai/benchmark?slug=xdailybench-quantitative-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-21.