List your company

Mathematical Reasoning on AIME 24 (Rank)

1RankQwen3-30B-A3B-Thinking-2507
0.245.3710.515.63Oct 5, 2025

Evaluation results

MethodLinks
Qwen3-30B-A3B-Thinking-2507Confidence Interval (CI)=w/ CI2025.101
Qwen3-30B-A3B-Thinking-2507Confidence Interval (CI)=w/o CI2025.101
Qwen3-4B-Thinking-2507Confidence Interval (CI)=w/ CI2025.102
Qwen3-4B-Thinking-2507Confidence Interval (CI)=w/o CI2025.102
gpt-oss-20b-highConfidence Interval (CI)=w/ CI2025.103
gpt-oss-20b-mediumConfidence Interval (CI)=w/ CI2025.103
gpt-oss-20b-mediumConfidence Interval (CI)=w/o CI2025.103
Phi-4-reasoning-plusConfidence Interval (CI)=w/ CI2025.103
Phi-4-reasoning-plusConfidence Interval (CI)=w/o CI2025.104
OpenThinker2-32BConfidence Interval (CI)=w/ CI2025.104
Light-R1-14B-DSConfidence Interval (CI)=w/ CI2025.104
FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32BConfidence Interval (CI)=w/ CI2025.104
gpt-oss-20b-highConfidence Interval (CI)=w/o CI2025.105
AceReason-Nemotron-1.1-7BConfidence Interval (CI)=w/ CI2025.105
Phi-4-reasoningConfidence Interval (CI)=w/ CI2025.105
gpt-oss-20b-lowConfidence Interval (CI)=w/ CI2025.106
Light-R1-14B-DSConfidence Interval (CI)=w/o CI2025.106
NVIDIA-Nemotron-Nano-9B-v2Confidence Interval (CI)=w/ CI2025.106
FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32BConfidence Interval (CI)=w/o CI2025.107
LIMO-v2Confidence Interval (CI)=w/ CI2025.107
OpenThinker2-32BConfidence Interval (CI)=w/o CI2025.108
EXAONE-4.0-1.2BConfidence Interval (CI)=w/ CI2025.108
AceReason-Nemotron-1.1-7BConfidence Interval (CI)=w/o CI2025.109
OpenR1-Distill-7BConfidence Interval (CI)=w/ CI2025.109
Phi-4-reasoningConfidence Interval (CI)=w/o CI2025.1010
OpenThinker3-1.5BConfidence Interval (CI)=w/ CI2025.1010
NVIDIA-Nemotron-Nano-9B-v2Confidence Interval (CI)=w/o CI2025.1011
OpenReasoning-Nemotron-1.5BConfidence Interval (CI)=w/ CI2025.1011
gpt-oss-20b-lowConfidence Interval (CI)=w/o CI2025.1012
DeepSeek-R1-Distill-Qwen-1.5BConfidence Interval (CI)=w/ CI2025.1012
Sky-T1-32B-FlashConfidence Interval (CI)=w/ CI2025.1012
LIMO-v2Confidence Interval (CI)=w/o CI2025.1013
Bespoke-Stratos-7BConfidence Interval (CI)=w/ CI2025.1013
EXAONE-4.0-1.2BConfidence Interval (CI)=w/o CI2025.1014
OpenR1-Distill-7BConfidence Interval (CI)=w/o CI2025.1015
OpenThinker3-1.5BConfidence Interval (CI)=w/o CI2025.1016
OpenReasoning-Nemotron-1.5BConfidence Interval (CI)=w/o CI2025.1017
Sky-T1-32B-FlashConfidence Interval (CI)=w/o CI2025.1018
DeepSeek-R1-Distill-Qwen-1.5BConfidence Interval (CI)=w/o CI2025.1019
Bespoke-Stratos-7BConfidence Interval (CI)=w/o CI2025.1020