Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Grade-school math on GSM8K
Loading...
59.2
Accuracy
MoE-Sieve (Qwen1.5-MoE-A2.7B)
29.248
37.024
44.8
52.576
Mar 25, 2026
Accuracy
Delta (Percentage Points)
95% CI Magnitude (Percentage Points)
Eqv@2pp Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
Accuracy
Delta (Percentage Points)
95% CI Magnitude (Percentage Points)
Eqv@2pp Score
MoE-Sieve (Qwen1.5-MoE-A2.7B)
Condition=Hot (25%)
2026.03
59.2
0.2
0.77
-
Qwen1.5-MoE-A2.7B
Condition=Full LoRA
2026.03
59
-
-
-
OLMoE-1B-7B
Condition=Full LoRA
2026.03
30.4
-
-
-
MoE-Sieve (OLMoE-1B-7B)
Condition=Hot (25%)
2026.03
30.4
0.08
1.45
-
Feedback
Search any
task
Search any
task