Online Self-Weighted Fine-Tuning
Not assessedPlan blockedFindingclaim-main-table1-qwen3-1-7b
OSW-FT (K=2) on Qwen3-1.7B-Base achieves 5.42% Pass@1 and 26.67% Pass@16 on AIME 24, 3.96% Pass@1 and 23.34% Pass@16 on AIME 25, 22.24% Pass@1 and 55.81% Pass@16 on AMC 22, 27.45% Pass@1 and 65.22% Pass@16 on AMC 23, 17.78% Pass@1 and 48.89% Pass@16 on AMC 24, 57.40% Pass@1 on MATH-500, and 26.27% Pass@1 on GPQA-Diamond.
Source: source-paper:Table 1, Section 4.2, page 5
Reported and observed measurements
pass_at_1
m-qwen3-1-7b-osw-aime24-p1
Reported 5.42 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-1-7b-osw-aime24-p16
Reported 26.67 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-1-7b-osw-aime25-p1
Reported 3.96 percentage_points
Observed — percentage_points
pass_at_16
m-qwen3-1-7b-osw-aime25-p16
Reported 23.34 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-1-7b-osw-math500-p1
Reported 57.4 percentage_points
Observed — percentage_points
pass_at_1
m-qwen3-1-7b-osw-gpqad-p1
Reported 26.27 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.