Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (PEEM & Overall Scores)
Loading...
95.3
Accuracy
GPT-4o-mini
54.688
65.2315
75.775
86.3185
Mar 11, 2026
Mar 20, 2026
Mar 29, 2026
Apr 7, 2026
Apr 16, 2026
Apr 25, 2026
May 5, 2026
Accuracy
PEEM Accuracy
Response Overall Score
Prompt Overall Score
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
PEEM Accuracy
Response Overall Score
Prompt Overall Score
GPT-4o-mini
Task Model=GPT-4o-mini
2026.03
95.3
4.882
4.847
4.701
Gemini-2.5-Flash
Task Model=Gemini-2.5-...
2026.03
94.1
4.81
4.855
4.712
Qwen-2.5-7B-IT
Task Model=Qwen-2.5-7B-IT
2026.03
86
4.654
4.723
4.506
LLaMA-3.1-8B-IT
Task Model=LLaMA-3.1-8...
2026.03
83.6
4.48
4.646
4.405
Echo-LoRA
Model=LLaMA2-7B
2026.05
58.61
-
-
-
Gemma-2-9B-IT
Task Model=Gemma-2-9B-IT
2026.03
57.1
4.354
4.582
4.125
Flat-LoRA
Model=LLaMA2-7B
2026.05
56.25
-
-
-
Feedback
Search any
task
Search any
task