List your company
ResearchFormerly WizWand

Embodied Decision Making on ALFWorld held-out (test)

95.5ScoreSkillOpt
25.71643.83361.9580.067May 22, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SkillOptModel=GPT–5.5, Harness=No harness / direct chat2026.0595.5
LLM skillModel=GPT–5.5, Harness=No harness / direct chat2026.0593.3
Human skillModel=GPT–5.5, Harness=No harness / direct chat2026.0591.8
SkillOptModel=GPT–5.4, Harness=No harness / direct chat2026.0591
Trace2SkillModel=GPT–5.5, Harness=No harness / direct chat2026.0587.3
GEPAModel=GPT–5.5, Harness=No harness / direct chat2026.0585.8
SkillOptModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0585.8
SkillOptModel=GPT–5.2, Harness=No harness / direct chat2026.0585.1
No skillModel=GPT–5.5, Harness=No harness / direct chat2026.0583.6
LLM skillModel=GPT–5.4, Harness=No harness / direct chat2026.0583.6
TextGradModel=GPT–5.5, Harness=No harness / direct chat2026.0582.8
Trace2SkillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0582.8
GEPAModel=GPT–5.2, Harness=No harness / direct chat2026.0582.8
SkillOptModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0582.1
GEPAModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0581.3
SkillOptModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0581.3
TextGradModel=GPT–5.4, Harness=No harness / direct chat2026.0578.4
Trace2SkillModel=GPT–5.2, Harness=No harness / direct chat2026.0576.9
TextGradModel=GPT–5.2, Harness=No harness / direct chat2026.0576.1
No skillModel=GPT–5.4, Harness=No harness / direct chat2026.0575.4
Human skillModel=GPT–5.4, Harness=No harness / direct chat2026.0574.6
GEPAModel=GPT–5.4, Harness=No harness / direct chat2026.0574.6
GEPAModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0573.9
Trace2SkillModel=GPT–5.4, Harness=No harness / direct chat2026.0573.1
No skillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0573.1
TextGradModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0570.9
Trace2SkillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0570.9
SkillOptModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0569.4
GEPAModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0568.7
No skillModel=GPT–5.2, Harness=No harness / direct chat2026.0568.7
LLM skillModel=GPT–5.2, Harness=No harness / direct chat2026.0568.7
TextGradModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0567.9
LLM skillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0565.7
LLM skillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0565.7
Trace2SkillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0564.9
GEPAModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0560.4
LLM skillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0560.4
No skillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0559.7
Trace2SkillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0558.2
Human skillModel=GPT–5.4-mini, Harness=No harness / direct chat2026.0556.7
Human skillModel=GPT–5.2, Harness=No harness / direct chat2026.0556.7
LLM skillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0555.2
TextGradModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0553.7
Human skillModel=Qwen3.6–35B-A3B, Harness=No harness / direct chat2026.0544.8
TextGradModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0542.5
No skillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0534.3
No skillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0530.6
Human skillModel=GPT–5.4-nano, Harness=No harness / direct chat2026.0529.9
Human skillModel=Qwen3.5–4B, Harness=No harness / direct chat2026.0528.4