Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Graduate-level Reasoning on GPQA-D (Score)
Loading...
61.1
Score
MTI
20.644
31.147
41.65
52.153
Oct 15, 2025
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
MTI
Model=Qwen3-8B, τ=1.5
2025.10
61.1
MTI
Model=Qwen3-8B, τ=0.5
2025.10
60.6
MTI
Model=Qwen3-8B, τ=1.0
2025.10
60.1
CGRS
Model=Qwen3-8B, τ=-
2025.10
59.8
DEER
Model=Qwen3-8B, τ=-
2025.10
59.3
TALE
Model=Qwen3-8B, τ=-
2025.10
59.1
Dynasor
Model=Qwen3-8B, τ=-
2025.10
57.7
NoThinking
Model=Qwen3-8B, τ=-
2025.10
54.2
MTI
Model=DeepSeek-R1-7B,...
2025.10
51.52
MTI
Model=DeepSeek-R1-7B,...
2025.10
48.5
MTI
Model=DeepSeek-R1-7B,...
2025.10
40.9
NoThinking
Model=DeepSeek-R1-7B, τ=-
2025.10
37.9
TALE
Model=DeepSeek-R1-7B, τ=-
2025.10
36.2
DEER
Model=DeepSeek-R1-7B, τ=-
2025.10
33.1
CGRS
Model=DeepSeek-R1-7B, τ=-
2025.10
32.8
Dynasor
Model=DeepSeek-R1-7B, τ=-
2025.10
22.2
Feedback
Search any
task
Search any
task
