List your company

Skill Evolution on SL-Bench

59AccuracyALIGNEVOSKILL
1.816.6531.546.35Jun 29, 2025

Evaluation results

MethodLinks
ALIGNEVOSKILLLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0659—
Trace2SkillLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0658—
SkillXLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0657—
CoEvoSkillsLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0656—
ALIGNEVOSKILLLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0654—
Trace2SkillLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0652—
SkillXLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0651—
CoEvoSkillsLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0650—
BaseLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0648—
BaseLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0642—
ALIGNEVOSKILLLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0641—
Trace2SkillLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0639—
SkillXLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0638.1—
ALIGNEVOSKILLLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0637—
CoEvoSkillsLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0636—
ALIGNEVOSKILLLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0635—
Trace2SkillLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0633—
Trace2SkillLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0632.9—
SkillXLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0632—
SkillXLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0631—
CoEvoSkillsLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0630—
BaseLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0630—
CoEvoSkillsLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0629—
ALIGNEVOSKILLLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0628—
ALIGNEVOSKILLLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0627—
Trace2SkillLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0626.1—
SkillXLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0625—
Trace2SkillLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0624.1—
CoEvoSkillsLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0624—
ALIGNEVOSKILLLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0622—
SkillXLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0622—
BaseLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0621—
CoEvoSkillsLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0621—
BaseLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0620—
Trace2SkillLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0618—
BaseLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0617—
SkillXLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0616—
CoEvoSkillsLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0615.1—
BaseLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0613—
BaseLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.064—