Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
STEM Reasoning on GPQA (Pass@1)
Loading...
77.06
Pass@1 Accuracy
GPT-OSS-120B
25.5176
38.8988
52.28
65.6612
Apr 10, 2026
Apr 22, 2026
May 4, 2026
May 17, 2026
May 29, 2026
Jun 10, 2026
Jun 23, 2026
Pass@1 Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
GPT-OSS-120B
Sampling Strategy=4-sa...
2026.04
77.06
GPT-5 Mini
Sampling Strategy=4-sa...
2026.04
75.46
Gemini 2.5 Flash
Sampling Strategy=4-sa...
2026.04
75.09
Aryabhata 2
Sampling Strategy=4-sa...
2026.04
74.86
Qwen3-30B-A3B (Thinking)
Sampling Strategy=4-sa...
2026.04
73.31
GPT-OSS-20B
Sampling Strategy=4-sa...
2026.04
70.51
Nemotron 3 Nano 30B A3B
Sampling Strategy=4-sa...
2026.04
65.38
GPT-5 Nano
Sampling Strategy=4-sa...
2026.04
61.11
TAC
Backbone=Qwen3-4B-Base...
2026.06
42.5
Random
Backbone=Qwen3-4B-Base...
2026.06
41.3
SEC
Backbone=Qwen3-4B-Base...
2026.06
36.7
SEC
Backbone=Qwen3-0.6B-Ba...
2026.06
29.5
Random
Backbone=Qwen3-0.6B-Ba...
2026.06
27.7
TAC
Backbone=Qwen3-0.6B-Ba...
2026.06
27.5
Feedback
Search any
task
Search any
task