List your company

Mathematical Problem Solving on LiveMath held-out (test)

78.4ScoreSkillOpt
4.35223.57642.862.024May 22, 2026

Evaluation results

MethodLinks
SkillOptModel=GPT–5.5, Harness=Codex harness2026.0578.4
SkillOptModel=GPT–5.5, Harness=No harness / direct chat2026.0566.9
EvoSkillModel=GPT–5.5, Harness=Codex harness2026.0563.2
SkillOptModel=GPT–5.5, Harness=Claude Code harness2026.0556.5
Trace2SkillModel=GPT–5.5, Harness=No harness / direct chat2026.0552
SkillOptModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0552
EvoSkillModel=GPT–5.5, Harness=Claude Code harness2026.0552
TextGradModel=GPT–5.5, Harness=No harness / direct chat2026.0549.2
Human skillModel=GPT–5.5, Harness=Codex harness2026.0548.8
LLM skillModel=GPT–5.5, Harness=Codex harness2026.0545.6
LLM skillModel=GPT–5.5, Harness=Claude Code harness2026.0544.8
SkillOptModel=GPT–5.4, Harness=No harness / direct chat2026.0544
Human skillModel=GPT–5.5, Harness=Claude Code harness2026.0544
GEPAModel=GPT–5.5, Harness=No harness / direct chat2026.0543.2
Human skillModel=GPT–5.4, Harness=No harness / direct chat2026.0541.6
GEPAModel=GPT–5.4, Harness=No harness / direct chat2026.0541.6
SkillOptModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0541.6
No skillModel=GPT–5.5, Harness=Claude Code harness2026.0540.8
LLM skillModel=GPT–5.5, Harness=No harness / direct chat2026.0540
Trace2SkillModel=GPT–5.4, Harness=No harness / direct chat2026.0540
Human skillModel=GPT–5.5, Harness=No harness / direct chat2026.0538.4
No skillModel=GPT–5.5, Harness=No harness / direct chat2026.0537.6
No skillModel=GPT–5.4, Harness=No harness / direct chat2026.0536.8
LLM skillModel=GPT–5.4, Harness=No harness / direct chat2026.0536.8
TextGradModel=GPT–5.4, Harness=No harness / direct chat2026.0536.6
SkillOptModel=GPT–5.2, Harness=No harness / direct chat2026.0536
No skillModel=GPT–5.5, Harness=Codex harness2026.0535.2
Trace2SkillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0532.8
SkillOptModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0532.8
No skillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0531.2
GEPAModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0531.2
Human skillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0529.6
Trace2SkillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0529.6
Human skillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0528.8
Trace2SkillModel=GPT–5.2, Harness=No harness / direct chat2026.0528.8
GEPAModel=GPT–5.2, Harness=No harness / direct chat2026.0528.8
LLM skillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0528.8
GEPAModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0528.8
LLM skillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0528
TextGradModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0527.2
GEPAModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0527.2
SkillOptModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0527.2
Trace2SkillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0527.2
Trace2SkillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0525.6
LLM skillModel=GPT–5.2, Harness=No harness / direct chat2026.0525.6
GEPAModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0524.8
LLM skillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0524.8
No skillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0523.2
Human skillModel=GPT–5.2, Harness=No harness / direct chat2026.0523.2
TextGradModel=GPT–5.2, Harness=No harness / direct chat2026.0522.4
No skillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0522.4
TextGradModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0520.8
No skillModel=GPT–5.2, Harness=No harness / direct chat2026.0520.8
LLM skillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0520
Human skillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0518.4
Human skillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0516.8
No skillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0514.7
TextGradModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0510.6
TextGradModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.057.2