Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematics on AIME 2024 (Accuracy)
Loading...
51.74
Accuracy
Cog-DRIFT
-1.3624
12.4238
26.21
39.9962
Apr 6, 2026
Accuracy
Updated 11d ago
Evaluation Results
Method
Method
Links
Accuracy
Cog-DRIFT
Base Model=Qwen3-4B-In...
2026.04
51.74
Zero-shot
Base Model=Qwen3-4B-In...
2026.04
46.92
NuRL (Prefix)
Base Model=Qwen3-4B-In...
2026.04
45.31
NuRL (Abstract)
Base Model=Qwen3-4B-In...
2026.04
44.81
Few-shot
Base Model=Qwen3-4B-In...
2026.04
44.78
RFT
Base Model=Qwen3-4B-In...
2026.04
40.06
GRPO
Base Model=Qwen3-4B-In...
2026.04
31.87
NuRL (Abstract)
Base Model=Llama3.2-3B...
2026.04
4.17
Cog-DRIFT
Base Model=Llama3.2-3B...
2026.04
4.17
Zero-shot
Base Model=Llama3.2-3B...
2026.04
3.75
Few-shot
Base Model=Llama3.2-3B...
2026.04
3.33
NuRL (Prefix)
Base Model=Llama3.2-3B...
2026.04
3.33
RFT
Base Model=Llama3.2-3B...
2026.04
1.67
GRPO
Base Model=Llama3.2-3B...
2026.04
0.68
Feedback
Search any
task
Search any
task