Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multilingual Mathematical Reasoning on MGSM (native CoT avg)
Loading...
87.73
Native CoT Avg Score
Nemotron-3-Ultra 550B-A55B-Base
81.0116
82.7558
84.5
86.2442
Jun 12, 2026
Native CoT Avg Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Native CoT Avg Score
Nemotron-3-Ultra 550B-A55B-Base
shots=8-shot, reasonin...
2026.06
87.73
Kimi-K2 Base
shots=8-shot, reasonin...
2026.06
85.2
Mistral-Large-3 675B-Base-2512
shots=8-shot, reasonin...
2026.06
82.93
DeepSeek-V3.2 Exp-Base
shots=8-shot, reasonin...
2026.06
82.33
GLM-4.5 Base
shots=8-shot, reasonin...
2026.06
81.27
Feedback
Search any
task
Search any
task