doubao-seed-evolving: benchmark results

Provider: ByteDance. Access: API.

Aggregate Rating 1851 ± 23, rank #33 of 1640 rated models, from 46 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
CLE - OpenClaw Trial 1 Level 54.17Cumulative pass rate (%)100
CLE - OpenClaw Trial 2 Level 48.33Cumulative pass rate (%)100
CLE - OpenClaw Trial 2 Level 56.67Cumulative pass rate (%)100
ReLE - Education - Gaokao69.3Accuracy (%)100
ReLE - Finance91.7Accuracy (%)100
ReLE - Education67.3Accuracy (%)98
ReLE - Medicine and Mental Health91Accuracy (%)98
ReLE - Reasoning and Mathematics88Accuracy (%)97.9
ReLE - Law - Lawyer Qualification Exam84Accuracy (%)96.9
ReLE - Education - High School Subjects77Accuracy (%)95.9
ReLE - Medicine - Physician Exams90.8Accuracy (%)95.9
ReLE - Overall75.5Accuracy (%)95

Interactive version: theaggregate.ai/model?slug=doubao-seed-evolving · How It Works · Data refreshed daily, snapshot 2026-11-07.