Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on MMLU-Pro
Loading...
191.3
Tokens Per Second (TPS)
PARSE + EAGLE3
88.34
115.07
141.8
168.53
May 5, 2026
Tokens Per Second (TPS)
Accuracy
Inference Speedup
Updated 27d ago
Evaluation Results
Method
Method
Links
Tokens Per Second (TPS)
Accuracy
Inference Speedup
PARSE + EAGLE3
Model=Qwen3-235B-A22B,...
2026.05
191.3
-
2.07
PARSE
Model=Qwen3-235B-A22B,...
2026.05
149.5
63.6
1.62
Eagle3
Model=Qwen3-235B-A22B,...
2026.05
137
-
1.48
Qwen3-235B-A22B
Model=Qwen3-235B-A22B,...
2026.05
92.3
66.8
-
Qwen3-8B
Model=Qwen3-8B, Decodi...
2026.05
-
56.8
-
Feedback
Search any
task
Search any
task