Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Modeling Efficiency on InfiniteBench
Loading...
9
Decoding Speedup
LAVA
0.8464
2.9632
5.08
7.1968
Mar 31, 2026
Apr 10, 2026
Apr 20, 2026
Apr 30, 2026
May 10, 2026
May 20, 2026
May 31, 2026
Decoding Speedup
Extra Computation
Extra Memory Usage
Updated 1d ago
Evaluation Results
Method
Method
Links
Decoding Speedup
Extra Computation
Extra Memory Usage
LAVA
2026.03
9
0.01
0.6
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
5.53
-
-
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
5.03
-
-
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
3.04
-
-
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
2.94
-
-
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
2.84
-
-
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
2.51
-
-
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
2.42
-
-
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
2.4
-
-
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
2.23
-
-
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
1.47
-
-
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
1.21
-
-
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
1.16
-
-
Feedback
Search any
task
Search any
task