Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH500 (Acc, TNFT, Tokens, Delay)
Loading...
64
Accuracy
Stream (Ours)
47.568
51.834
56.1
60.366
May 12, 2026
Accuracy
TNFT
Output Tokens
Latency
Updated 21d ago
Evaluation Results
Method
Method
Links
Accuracy
TNFT
Output Tokens
Latency
Stream (Ours)
Model=Qwen3-4B
2026.05
64
0
742.26
26.51
Vanilla
Model=Qwen3-4B
2026.05
60.8
103.16
1,363.95
45.82
Base
Model=Qwen3-4B
2026.05
60
130.1
3,678.51
126.9
Stream (Ours)
Model=Qwen3-1.7B
2026.05
51.6
0
803
22.94
Base
Model=Qwen3-1.7B
2026.05
48.4
130.1
3,229.16
88.15
Vanilla
Model=Qwen3-1.7B
2026.05
48.2
103.16
1,612.76
43.14
Feedback
Search any
task
Search any
task