Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Reasoning on RACE
Loading...
86.51
Accuracy
Qwen2.5-7B
0.5436
22.8618
45.18
67.4982
Feb 4, 2026
Feb 26, 2026
Mar 20, 2026
Apr 11, 2026
May 3, 2026
May 25, 2026
Jun 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-7B
2026.02
86.51
BioBridge
2026.02
84
Sumi-7B
Paradigm=Uniform Diffu...
2026.06
41.4
Llama 2-7B
Paradigm=AR, Training...
2026.06
39.5
Llama 3-8B
Paradigm=AR, Training...
2026.06
39.2
LLaDA-8B
Paradigm=Masked Diffus...
2026.06
38.7
Falcon-7B
Paradigm=AR, Training...
2026.06
38.3
OLMo-7B
Paradigm=AR, Training...
2026.06
37.9
Prot2Chat
2026.02
21.58
ProtT3
2026.02
3.85
Feedback
Search any
task
Search any
task