xDailyBench - Implicit Rubrics: leaderboard
xDailyBench rubric-level score pooled over requirements the user left implicit -- the harder half, and the one that separates the field. Higher is better. Source: arxiv.org/abs/2609.07784.
Metric: Score (%). Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 67.6 | #35 |
| 2 | GPT-5.6 Sol | 66 | #22 |
| 3 | GPT-5.5 | 62.3 | #33 |
| 4 | Claude Opus 4.7 | 61.8 | #52 |
| 5 | Qwen 3.7 Max | 56.8 | #86 |
| 6 | DeepSeek V4 Pro | 53.5 | #112 |
| 7 | GLM-5.1 | 52.5 | #109 |
| 8 | Kimi K2.6 | 52.1 | #113 |
| 9 | Qwen 3.6 Max | 50.7 | #100 |
| 10 | Gemini 3.1 Pro (Preview) | 39.5 | #65 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=xdailybench-implicit-rubrics · How It Works · Data refreshed daily, snapshot 2026-11-06.