MRCR-v2 128k — leaderboard
MRCR-v2 long-context retrieval subset using a 128K context window with 8 needles, as reported in Qwen's Qwen3.7-Max launch post.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Plus | 91.7 |
| 2 | Qwen 3.7 Max (Max) | 90.4 |
| 3 | Qwen 3.6 Plus | 85.9 |
| 4 | Claude Opus 4.6 (Max) | 84 |
| 5 | DeepSeek V4 Pro (Max) | 74.4 |
| 6 | Gemma 4 31B | 66.4 |
| 7 | GLM-5.1 | 62 |
| 8 | Gemma 4 26B A4B | 44.1 |
| 9 | Gemma 4 12B | 43.4 |
| 10 | Gemma 4 E4B | 25.4 |
| 11 | Gemma 4 E2B | 19.1 |
Interactive version: theaggregate.ai/benchmark?slug=mrcr-v2-128k · How the rankings work · Data refreshed daily, snapshot 2026-07-22.