Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-step Reasoning on Big-Bench Hard
Loading...
71.02
Accuracy
Ouro-1.4B-R4
6.9872
23.6111
40.235
56.8589
Jun 3, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Ouro-1.4B-R4
Total Parameters=1.4B,...
2026.06
71.02
Qwen-3-1.7B
Total Parameters=1.7B,...
2026.06
53.51
PowerMoE-3B
Total Parameters=3B, A...
2026.06
33.07
LoopMoE
Total Parameters=3B, A...
2026.06
27.94
OLMoE-1B-7B
Total Parameters=7B, A...
2026.06
26.85
Vanilla MoE
Total Parameters=3B, A...
2026.06
26.12
Pythia-1.4B
Total Parameters=1.4B,...
2026.06
23.71
OLMo2-1B
Total Parameters=1.0B,...
2026.06
9.45
Feedback
Search any
task
Search any
task