Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH 500 (Accuracy and Delta Change)
Loading...
98.8
Accuracy
DeepSeek-R1-0528
86.32
89.56
92.8
96.04
Apr 3, 2026
Accuracy
Accuracy Delta (%)
Updated 13d ago
Evaluation Results
Method
Method
Links
Accuracy
Accuracy Delta (%)
DeepSeek-R1-0528
Thinking Mode=Thinking
2026.04
98.8
7.2
Qwen3-30B-A3B-Thinking
Thinking Mode=Thinking
2026.04
97.5
10.5
Qwen3-8B
Thinking Mode=Thinking
2026.04
96.4
11.1
DeepSeek-V3.1
Thinking Mode=No Thinking
2026.04
92.2
-
Qwen3-30B-A3B-Instruct
Thinking Mode=No Thinking
2026.04
88.2
-
Qwen3-8B
Thinking Mode=No Thinking
2026.04
86.8
-
Feedback
Search any
task
Search any
task