Skip to content

Benchmark

MRCR · 1M · MMR

Scores are percentages. Higher is better.

Models measured
1
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

64.4%
Mean
76.9%
Median
19%
Std dev
37.5%
10th percentile
78.7%
90th percentile
37.5%
Min
37.5%78.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1DeepSeek V4 FlashDeepSeek V4 official model card · Think Max· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.7%
2DeepSeek V4 FlashDeepSeek V4 official model card · Think High· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.9%
3DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.37.5%

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.