Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multilingual Knowledge Evaluation on Global-MMLU Low
Loading...
52.31
Accuracy
GRPO
28.4004
34.6077
40.815
47.0223
Jun 4, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GRPO
Backbone=Qwen-2.5-7B
2026.06
52.31
Baseline
Backbone=Qwen-2.5-7B
2026.06
52.19
CPT + SFT
Backbone=Qwen-2.5-7B
2026.06
51.19
CPT + GRPO
Backbone=Qwen-2.5-7B
2026.06
50
CPT
Backbone=Qwen-2.5-7B
2026.06
49.19
SFT
Backbone=Qwen-2.5-7B
2026.06
46.75
GRPO
Backbone=OLMo-2-1124-7B
2026.06
32
Baseline
Backbone=OLMo-2-1124-7B
2026.06
31.79
CPT + SFT
Backbone=OLMo-2-1124-7B
2026.06
30.88
SFT
Backbone=OLMo-2-1124-7B
2026.06
30.32
CPT + GRPO
Backbone=OLMo-2-1124-7B
2026.06
29.61
CPT
Backbone=OLMo-2-1124-7B
2026.06
29.32
Feedback
Search any
task
Search any
task
