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

Mathematical Reasoning on AIME 26

86.7Score

Gpt-oss-20b-high

Updated 5d ago

Evaluation Results

Method	Links
Gpt-oss-20b-high 2026.03		86.7
Qwen3-14B 2026.03		86.7
Qwen3-30B-A3B 2026.03		86.7
EngGPT2-16B-A3B 2026.03		70
p1 2026.04		62.24
p1 2026.04		57.24
p1 2026.04		55.68
p1 2026.04		55.21
RL 2026.04		54.58
base 2026.04		54.38
GEPA 2026.04		54.22
GEPA 2026.04		53.91
GEPA 2026.04		53.49
p1 2026.04		51.25
p1 2026.04		37.6
gemma-3-12b-it 2026.03		36.7
p1 2026.04		36.15
p1 2026.04		35.99
RL 2026.04		35.89
p1 2026.04		35.63
base 2026.04		35.57
GEPA 2026.04		35.52
GEPA 2026.04		35.26
GEPA 2026.04		35.1
p1 2026.04		33.23
Entropy-Cut MH 2026.05		13.1
SMC 2026.05		11.8
TMC 2026.05		10.6
Entropy-Cut MH 2026.05		10.3
SMC 2026.05		10.1
Moonlight-16B-A3B-Instruct 2026.03		10
TMC 2026.05		9.8
Uniform-Cut MH 2026.05		9.5
Uniform-Cut MH 2026.05		9.5
TMC 2026.05		9.4
Entropy-Cut MH 2026.05		9.4
Entropy-Cut MH 2026.05		8.7
SMC 2026.05		8.6
Uniform-Cut MH 2026.05		8.2
Uniform-Cut MH 2026.05		8
SMC 2026.05		7.4
TMC 2026.05		6.9
Low-Temperature 2026.05		6.8
Low-Temperature 2026.05		6.4
Low-Temperature 2026.05		6.4
Low-Temperature 2026.05		5.7
Standard 2026.05		4.8
Standard 2026.05		3.5
Standard 2026.05		3.2
Entropy-Cut MH 2026.05		3.1
TMC 2026.05		3
Uniform-Cut MH 2026.05		2.9
Standard 2026.05		2
SMC 2026.05		1.7
Low-Temperature 2026.05		1.6
Standard 2026.05		0.6
Llama-3.1-8B-Instruct 2026.03		0.1
gemma-2-9b-it 2026.03		0