OSW-FT (K=2) on Qwen3-0.6B-Base achieves 0.83% Pass@1 and 6.67% Pass@16 on AIME 24, 1.04% Pass@1 and 10.00% Pass@16 on AIME 25, 8.72% Pass@1 and 41.86% Pass@16 on AMC 22, 13.04% Pass@1 and 56.52% Pass@16 on AMC 23, 5.14% Pass@1 and 28.89% Pass@16 on AMC 24, 24.20% Pass@1 on MATH-500, and 20.20% Pass@1 on GPQA-Diamond, matching or outperforming standard SFT across all evaluated benchmarks.
Source: source-paper:Table 1, Section 4.2, page 5
Reported and observed measurements
pass_at_1
m-qwen3-0-6b-osw-aime24-p1
Reported 0.83 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-0-6b-osw-aime24-p16
Reported 6.67 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-0-6b-osw-aime25-p1
Reported 1.04 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-0-6b-osw-aime25-p16
Reported 10 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-0-6b-osw-amc22-p1
Reported 8.72 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-0-6b-osw-amc22-p16
Reported 41.86 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-0-6b-osw-amc23-p1
Reported 13.04 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-0-6b-osw-amc23-p16
Reported 56.52 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-0-6b-osw-amc24-p1
Reported 5.14 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-0-6b-osw-amc24-p16
Reported 28.89 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-0-6b-osw-math500-p1
Reported 24.2 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-0-6b-osw-gpqad-p1
Reported 20.2 percentage_points
Observed — percentage_points
Assessments (0)
No immutable Assessment has been published for this Claim yet.
Runs (0)
No execution has been linked to this Claim yet.