Skip to content

Benchmark

MRCR v2 · 256K

Scores are percentages. Higher is better.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

89.2%
Mean
92.9%
Median
4.4%
Std dev
83.2%
10th percentile
93.8%
90th percentile
83.2%
Min
83.2%93.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-5.6 SolQwen表:MRCR v2 · 256K · 8-needle· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.8%
2Qwen3.8 MaxQwen表:MRCR v2 · 256K · 8-needle· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.9%
3Qwen3.7 MaxQwen表:MRCR v2 · 256K · 8-needle· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.7%
4Claude Opus 4.8Qwen表:MRCR v2 · 256K · 8-needle· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.2%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.