Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Expert-level Science Question Answering on GPQA Diamond
Loading...
78
Score
gpt-oss-120b
24.1904
38.1602
52.13
66.0998
Jan 11, 2026
Jan 27, 2026
Feb 13, 2026
Mar 2, 2026
Mar 18, 2026
Apr 4, 2026
Apr 21, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
gpt-oss-120b
Number of Parameters=1...
2026.01
78
GLM-4.5-Air
Number of Parameters=110B
2026.01
75.8
gpt-oss-120b
Number of Parameters=1...
2026.01
69.4
Solar Open
Number of Parameters=102B
2026.01
68.1
Base
Model=Qwen-2.5-7B-Inst...
2026.04
36.36
POP
Model=Qwen-2.5-7B, Eva...
2026.04
35.35
Base
Model=Qwen-2.5-7B, Eva...
2026.04
33.84
POP
Model=Qwen-2.5-7B-Inst...
2026.04
33.84
Train on D
Model=Qwen-2.5-7B, Eva...
2026.04
28.28
Train on D
Model=Qwen-2.5-7B-Inst...
2026.04
26.26
Feedback
Search any
task
Search any
task