List your company

Math Reasoning on AIME 2026 (avg@8)

90.4AIME 2026 Avg ScoreNo Skill
-3.09621.17745.4569.723Mar 26, 2026

Evaluation results

MethodLinks
No SkillSkill User=122B2026.0390.4
No SkillSkill User=35B2026.0383.3
Trace2Skill (122B-Authored +Error)Skill User=35B, Condition=122B-Authored +Error2026.035
Trace2Skill (122B-Authored +Error)Skill User=122B, Condition=122B-Authored +Error2026.032.9
Trace2Skill (35B-Authored +Error)Skill User=122B, Condition=35B-Authored +Error2026.031.3
Trace2Skill (35B-Authored +Error)Skill User=35B, Condition=35B-Authored +Error2026.030.5