Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
End-to-end Text Generation on NVIDIA B200 GPU Overall Generation
Loading...
4,920.12
Throughput (tokens/s)
YOCO (CLSA)
-131.7736
1,179.7757
2,491.325
3,802.8743
Jun 4, 2026
Throughput (tokens/s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Throughput (tokens/s)
YOCO (CLSA)
Context Length=8K, Har...
2026.06
4,920.12
YOCO (Dense)
Context Length=8K, Har...
2026.06
4,311.58
YOCO (CLSA)
Context Length=16K, Ha...
2026.06
3,715.19
Transformer
Context Length=8K, Har...
2026.06
2,989.78
YOCO (Dense)
Context Length=16K, Ha...
2026.06
2,904.96
YOCO (CLSA)
Context Length=32K, Ha...
2026.06
2,805.48
YOCO (Dense)
Context Length=32K, Ha...
2026.06
1,832.66
YOCO (CLSA)
Context Length=64K, Ha...
2026.06
1,735.59
Transformer
Context Length=16K, Ha...
2026.06
1,449.91
YOCO (CLSA)
Context Length=128K, H...
2026.06
1,068.06
YOCO (Dense)
Context Length=64K, Ha...
2026.06
1,042.9
YOCO (Dense)
Context Length=128K, H...
2026.06
599.05
Transformer
Context Length=32K, Ha...
2026.06
570.27
Transformer
Context Length=64K, Ha...
2026.06
191.36
Transformer
Context Length=128K, H...
2026.06
62.53
Feedback
Search any
task
Search any
task