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

Math on GSM8K

0.988Accuracy

BERT-Judge

Updated 1mo ago

Evaluation Results

Method	Links
BERT-Judge 2026.04		0.988
POES 2026.04		0.972
GPT-4o 2026.03		0.971
POES 2026.04		0.965
Claude 3.5 Sonnet 2026.03		0.964
Gemini 2.5 Pro 2026.03		0.958
Random 2026.04		0.958
POES 2026.04		0.953
IPOMP 2026.04		0.952
SESS 2026.04		0.952
Anchor 2026.04		0.952
Qwen2.5-14B-Instruct-1M 2025.08		0.95
POES 2026.04		0.95
Anchor 2026.04		0.95
IPOMP 2026.04		0.95
POES 2026.04		0.948
Anchor 2026.04		0.948
EcoThink 2026.03		0.945
Random 2026.04		0.945
Regex 2026.04		0.944
Prediction 2026.04		0.943
IPOMP 2026.04		0.942
Prediction 2026.04		0.94
SESS 2026.04		0.94
Random 2026.04		0.94
MAN 2026.06		0.937
SESS 2026.04		0.935
Prediction 2026.04		0.935
MSAN 2026.06		0.935
NPG-Muse-8B 2025.08		0.933
Anchor 2026.04		0.932
Random 2026.04		0.93
Prediction 2026.04		0.93
SESS 2026.04		0.927
SESS 2026.04		0.925
SDAR-30B-A3B 2026.04		0.9249
Full 2026.06		0.923
IPOMP 2026.04		0.922
Qwen3-14B + NGM 2026.05		0.9174
Qwen3-14B 2026.05		0.9166
AutoMR 2025.10		0.915
Random 2026.04		0.915
SDAR-8B-Chat 2026.04		0.9136
SEER 2026.06		0.913
MoNE 2026.06		0.911
IPOMP 2026.04		0.91
Anchor 2026.04		0.91
EAN 2026.06		0.91
IPOMP 2026.04		0.907
Prediction 2026.04		0.907
Qwen3.5-35B-A3B-Base 2026.04		0.905
Frequency 2026.06		0.904
Qwen3-30B-A3B-Base 2026.04		0.903
OLMo3-7B-Instruct 2026.01		0.901
Qwen3-14B-Base 2025.08		0.9
HILA 2026.03		0.8986
Qwen3-8B 2026.01		0.898
Molmo2-8B 2026.01		0.897
Prediction 2026.04		0.897
DeepSeek-V3-Base 2026.01		0.893
Anchor 2026.04		0.892
AdaRAS 2026.01		0.8908
Qwen3-8B + NGM 2026.05		0.8908
Molmo2-O-7B 2026.01		0.89
POES 2026.04		0.89
NPG-Muse-7B 2025.08		0.889
Qwen2.5-7B-Instruct-1M 2025.08		0.888
rStar 2025.10		0.887
JoyAI-LLM Flash-Base 2026.04		0.887
LLaDA2.0-mini 2026.04		0.8848
Qwen3-8B 2026.05		0.884
CoT 2026.01		0.8832
Probing 2026.01		0.8832
MRP 2025.10		0.882
Full-FT 2026.03		0.881
REAP 2026.06		0.879
Qwen3-4B 2026.01		0.878
OpenReasoning-Nemotron-1.5B 2026.01		0.8757
Qwen3-4B + NGM 2026.05		0.8734
Kimi-Linear-48B-A3B-Instruct 2025.10		0.873
ICaRus 2026.02		0.873
Qwen3-4B 2026.05		0.8726
Meta-Reasoner 2025.10		0.87
Molmo2-4B 2026.01		0.866
FrugalGPT (Cascade) 2026.03		0.865
MaAS 2025.10		0.864
LLaDA2.1-mini 2026.04		0.8613
Yuan3.0-1T Base 2026.01		0.861
OLMo 3 2026.01		0.86
Full-FT 2026.03		0.858
Full-FT 2026.03		0.858
Kimi-Linear-48B-A3B-Instruct 2025.10		0.858
SUN 2026.03		0.855
SUN 2026.03		0.854
Multi Model 2026.02		0.854
CoT 2025.10		0.853
Random 2026.04		0.853
Qwen3-8B-Base 2025.08		0.852
QSUN 2026.03		0.851
REFUSION 2025.12		0.8491

Showing 100 of 248 rows