Judgemark v4: leaderboard
Metric: Judgemark Score (0-100). Source: eqbench.com. Saturation forecast: Around February 2027. 42 models tracked. Updated 18 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 90.73 | #110 |
| 2 | GPT-5.5 | 87.81 | #50 |
| 3 | Claude Opus 4.7 | 83.96 | #82 |
| 4 | Gemini 3.7 Flash | 83.39 | #38 |
| 5 | Claude Sonnet 4.6 | 82.15 | #171 |
| 6 | Muse Spark 1.2 | 79.4 | #98 |
| 7 | Claude Opus 5 | 78.81 | #24 |
| 8 | Gemini 3.1 Pro (Preview) | 78.69 | #99 |
| 9 | Claude Opus 4.8 | 77.96 | #62 |
| 10 | Grok 4.5 | 77.07 | #88 |
| 11 | GLM-5.2 | 73.19 | #150 |
| 12 | GLM-5.3 | 72.59 | #72 |
| 13 | Gemma 4 31B (IT) | 72.31 | #347 |
| 14 | GPT-5.4 | 72.08 | #133 |
| 15 | Claude Sonnet 5 | 70.89 | #116 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=judgemark-v4 · How It Works · Data refreshed daily, snapshot 2026-11-18.