Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Question Answering on SuperGPQA*
Loading...
62.4
Accuracy
GPT-5
39.624
45.537
51.45
57.363
Aug 26, 2025
Accuracy
Performance Delta
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Performance Delta
GPT-5
Reasoning Effort=High
2025.08
62.4
3.8
Gemini-2.5-Pro
Reasoning Effort=High
2025.08
60.4
0.3
Gemini-2.5-Pro
Reasoning Effort=Low
2025.08
60.1
-
o3
Reasoning Effort=High
2025.08
59.5
4.6
GPT-5
Reasoning Effort=Low
2025.08
58.6
-
o4-mini
Reasoning Effort=High
2025.08
57.1
8.5
o3
Reasoning Effort=Low
2025.08
54.9
-
o3-mini
Reasoning Effort=High
2025.08
54
13.5
Claude-Sonnet-4
Reasoning Effort=High
2025.08
49.8
4.6
o4-mini
Reasoning Effort=Low
2025.08
48.6
-
Claude-Sonnet-4
Reasoning Effort=Low
2025.08
45.2
-
o3-mini
Reasoning Effort=Low
2025.08
40.5
-
Feedback
Search any
task
Search any
task