CharXiv-R — leaderboard
CharXiv-R evaluates model capability on multimodal tasks from the linked upstream source with Score as the primary reported metric.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Mythos 5 | 93.5 |
| 2 | Claude Mythos Preview | 92.5 |
| 3 | Claude Opus 4.7 | 90.1 |
| 4 | Claude Opus 4.8 | 89.9 |
| 5 | Claude Sonnet 5 | 88.3 |
| 6 | Qwen 3.7 Plus | 85.9 |
| 7 | Claude Sonnet 4.6 | 85.3 |
| 8 | GPT-5.4 | 84.5 |
| 9 | Gemini 3.1 Pro (Preview) | 84.4 |
| 10 | Gemini 3.5 Flash | 84.2 |
| 11 | Qwen 3.6 Plus | 81.5 |
| 12 | Claude Opus 4.6 (Max) | 66 |
Interactive version: theaggregate.ai/benchmark?slug=charxiv-r · How the rankings work · Data refreshed daily, snapshot 2026-07-22.