Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Reasoning on GPQA (GPQA Metric)
Loading...
35.04
GPQA Accuracy
INSIGHT
25.992
28.341
30.69
33.039
Mar 2, 2026
GPQA Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
GPQA Accuracy
INSIGHT
Model=Qwen3-4B
2026.03
35.04
RANDOM
Model=Qwen3-4B
2026.03
34.38
EXPECTED-DIFFICULTY
Model=Qwen3-4B
2026.03
33.5
INVERSE-EVIDENCE
Model=Qwen3-4B
2026.03
33.48
MOPPS
Model=Qwen3-4B
2026.03
33.26
INSIGHT
Model=Qwen3-1.7B
2026.03
30.36
RANDOM
Model=Qwen3-1.7B
2026.03
30.2
MOPPS
Model=Qwen3-1.7B
2026.03
30.1
INVERSE-EVIDENCE
Model=Qwen3-1.7B
2026.03
29.69
INSIGHT
Model=Qwen3-0.6B
2026.03
29.5
INVERSE-EVIDENCE
Model=Qwen3-0.6B
2026.03
29.46
MOPPS
Model=Qwen3-0.6B
2026.03
27.9
RANDOM
Model=Qwen3-0.6B
2026.03
26.34
Feedback
Search any
task
Search any
task