Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Accuracy, TPS, Speedup)
Loading...
420.7
Throughput (tok/s)
PARSE + EAGLE3
81.244
169.372
257.5
345.628
May 5, 2026
Throughput (tok/s)
Accuracy
Speedup (×)
Updated 27d ago
Evaluation Results
Method
Method
Links
Throughput (tok/s)
Accuracy
Speedup (×)
PARSE + EAGLE3
Model=Qwen3-235B-A22B,...
2026.05
420.7
-
4.46
PARSE
Model=Qwen3-235B-A22B,...
2026.05
405
95.2
4.29
Eagle3
Model=Qwen3-235B-A22B,...
2026.05
176.4
-
1.87
Qwen3-235B-A22B
Model=Qwen3-235B-A22B,...
2026.05
94.3
94.8
-
Qwen3-8B
Model=Qwen3-8B, Decodi...
2026.05
-
94
-
Feedback
Search any
task
Search any
task