Share your thoughts, 1 month free Claude Pro on usSee more

Mathematical Reasoning on AIME (Acceptance length τ)

4.757Acceptance Length (τ)

Llama-3-8B

Updated 1mo ago

Evaluation Results

Method	Links
Llama-3-8B 2026.06		4.757
Llama 3.2-3B 2026.06		4.197
Llama-3-8B 2026.06		3.465
Llama 3.2-3B 2026.06		3.455
Llama 3.2-3B 2026.06		3.356
Llama-3-8B 2026.06		3.152
Llama 3.2-3B 2026.06		3.003
Llama-3-8B 2026.06		2.705
Qwen3-8B 2026.06		2.558
Qwen3-4B 2026.06		2.554
Qwen3-4B 2026.06		2.357
Qwen3-8B 2026.06		2.351
Qwen3-4B 2026.06		2.253
Qwen3-8B 2026.06		2.233
Qwen3-4B 2026.06		2.133
Qwen3-8B 2026.06		2.03