MRCR-v2 128k

MRCR-v2 long-context retrieval subset using a 128K context window with 8 needles, as reported in Qwen's Qwen3.7-Max launch post.

6rows
scoreprimary metric
2026-05-28sampled

Metadata

ID
mrcr_v2_128k
Category
Long Context
Release
Unknown

Metrics

Score

Latest Results

Provider-published Qwen3.7-Max comparison scores. Rows are marked self-reported and should be interpreted as source claims unless independently reproduced.

Rank Subject Score Model Match Provenance Sampled
1 Qwen3.7 Max 90.4% Qwen3.7 Max
qwen-qwen3.7-max
 		Self-reported 2026-05-28
2 Qwen3.6 Plus 85.9% Qwen3.6 Plus
qwen-qwen3.6-plus
 		Self-reported 2026-05-28
3 Claude Opus 4.6 Max 84% Claude Opus 4.6
anthropic-claude-opus-4.6
 		Self-reported 2026-05-28
4 DeepSeek V4 Pro Max 74.4% DeepSeek V4 Pro
deepseek-deepseek-v4-pro
 		Self-reported 2026-05-28
5 Kimi K2.6 Thinking 63.1% KIMI MoonshotAI: Kimi K2.6
moonshotai-kimi-k2.6
 		Self-reported 2026-05-28
6 GLM-5.1 Thinking 62% GLM GLM 5.1
z-ai-glm-5.1
 		Self-reported 2026-05-28