Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Average Performance on AIME 2024, GPQA Diamond, IFEval, and LiveCodeBench v6
Loading...
73.86
Average Score
Original
7.3208
24.5954
41.87
59.1446
Jun 9, 2026
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Score
Original
Model=Seed-OSS-36B-Ins...
2026.06
73.86
SpenseGPT+
Model=Seed-OSS-36B-Ins...
2026.06
73.12
SpenseGPT
Model=Seed-OSS-36B-Ins...
2026.06
71.69
Original
Model=Qwen3-32B, MLP S...
2026.06
71.68
SpenseGPT+
Model=Qwen3-32B, MLP S...
2026.06
70.76
SpenseGPT+
Model=Seed-OSS-36B-Ins...
2026.06
70.35
SpenseGPT
Model=Seed-OSS-36B-Ins...
2026.06
70.25
SpenseGPT+
Model=Qwen3-32B, MLP S...
2026.06
67.79
SpenseGPT
Model=Qwen3-32B, MLP S...
2026.06
67.21
SpenseGPT
Model=Qwen3-32B, MLP S...
2026.06
65.38
SparseGPT
Model=Seed-OSS-36B-Ins...
2026.06
65.18
SparseGPT
Model=Qwen3-32B, MLP S...
2026.06
60.27
HyperPrune
Model=Qwen3-32B, MLP S...
2026.06
24.22
Wanda
Model=Qwen3-32B, MLP S...
2026.06
18.96
HyperPrune
Model=Seed-OSS-36B-Ins...
2026.06
10.71
Wanda
Model=Seed-OSS-36B-Ins...
2026.06
9.88
Feedback
Search any
task
Search any
task