List your company

Skill Evolution on SRA-Bench

77.3AccuracyALIGNEVOSKILL
42.25251.35160.4569.549Jun 29, 2025

Evaluation results

MethodLinks
ALIGNEVOSKILLLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0677.3—
Trace2SkillLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0675.7—
SkillXLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0675.3—
ALIGNEVOSKILLLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0675.1—
CoEvoSkillsLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0674.9—
Trace2SkillLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0673.7—
SkillXLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0673.2—
CoEvoSkillsLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0672.6—
ALIGNEVOSKILLLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0672.2—
BaseLLM=GPT-5.4, Evolution Setting=Human-Labeled2025.0670.7—
Trace2SkillLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0669.8—
SkillXLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0669.2—
BaseLLM=DEEPSEEK-V4-FLASH, Evolution Setting=Human-Labeled2025.0668.9—
CoEvoSkillsLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0668.6—
ALIGNEVOSKILLLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0668.1—
ALIGNEVOSKILLLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0667.8—
Trace2SkillLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0666.4—
Trace2SkillLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0665.8—
SkillXLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0665.7—
SkillXLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0665.3—
CoEvoSkillsLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0664.8—
CoEvoSkillsLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0664.2—
BaseLLM=GPT-5.4, Evolution Setting=From-Scratch2025.0664.1—
ALIGNEVOSKILLLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0662.4—
BaseLLM=CLAUDE-HAIKU-4.5, Evolution Setting=Human-Labeled2025.0660.2—
BaseLLM=DEEPSEEK-V4-FLASH, Evolution Setting=From-Scratch2025.0660—
Trace2SkillLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0659.3—
SkillXLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0658.6—
ALIGNEVOSKILLLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0658—
CoEvoSkillsLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0657.9—
Trace2SkillLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0655.9—
ALIGNEVOSKILLLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0655.5—
SkillXLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0654.9—
CoEvoSkillsLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0653.6—
Trace2SkillLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0652.1—
BaseLLM=CLAUDE-HAIKU-4.5, Evolution Setting=From-Scratch2025.0651.8—
SkillXLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0651.5—
CoEvoSkillsLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0650.3—
BaseLLM=GPT-5.4-NANO, Evolution Setting=Human-Labeled2025.0647.3—
BaseLLM=GPT-5.4-NANO, Evolution Setting=From-Scratch2025.0643.6—