Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Knowledge on GPQA
Loading...
33.3
Accuracy
I-DPO + MaPPO
27.268
28.834
30.4
31.966
Jul 27, 2025
Sep 12, 2025
Oct 30, 2025
Dec 16, 2025
Feb 2, 2026
Mar 21, 2026
May 8, 2026
Accuracy
Updated 21d ago
Evaluation Results
Method
Method
Links
Accuracy
I-DPO + MaPPO
Model=Qwen2.5-7B-Instruct
2025.07
33.3
DPO + MaPPO
Model=Qwen2.5-7B-Instruct
2025.07
33.1
I-DPO
Model=Qwen2.5-7B-Instruct
2025.07
33
DPO
Model=Qwen2.5-7B-Instruct
2025.07
32
IT
Model=Qwen2.5-7B-Instruct
2025.07
31.5
IT
Model=Llama-3-8B-Instruct
2025.07
30.2
IT
Base Model=Llama-3-8B-...
2026.05
30.2
I-DPO
Model=Llama-3-8B-Instruct
2025.07
29.8
I-DPO
Base Model=Llama-3-8B-...
2026.05
29.8
DPO + MaPPO
Model=Llama-3-8B-Instruct
2025.07
29.5
DPO + MaPPO
Base Model=Llama-3-8B-...
2026.05
29.5
I-DPO + MaPPO
Model=Llama-3-8B-Instruct
2025.07
28.8
I-DPO + MaPPO
Base Model=Llama-3-8B-...
2026.05
28.8
DPO
Model=Llama-3-8B-Instruct
2025.07
27.5
DPO
Base Model=Llama-3-8B-...
2026.05
27.5
Feedback
Search any
task
Search any
task