Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Scientific Question Answering on GPQA (Accuracy & Response Length)
Loading...
70.7
Accuracy
AIM
53.852
58.226
62.6
66.974
Jan 7, 2026
Accuracy
Avg Response Length
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Avg Response Length
AIM
Method Category=Data-d...
2026.01
70.7
8,007
Qwen3-4B-Thinking
Method Category=Base M...
2026.01
67.7
9,032
RPAM
Method Category=Data-d...
2026.01
66.7
7,612
Ada-R1
Method Category=Traini...
2026.01
65.7
6,395
CoD
Method Category=Prompt...
2026.01
65.2
6,733
Average Merging
Method Category=Data-f...
2026.01
64.7
7,680
TIES Merging
Method Category=Data-f...
2026.01
63.6
6,598
Task Arithmetic
Method Category=Data-f...
2026.01
62.1
6,191
ACM
Method Category=Data-d...
2026.01
61.6
6,141
DARE-Linear
Method Category=Data-f...
2026.01
58.6
6,404
Qwen3-4B-Instruct
Method Category=Base M...
2026.01
54.5
5,086
Feedback
Search any
task
Search any
task