Doubao-Seed-1-8-251228: benchmark results

Provider: ByteDance. Released 2025-12-28. Access: API.

Unified ELO 1798 ± 33, rank #77 of 1607 rated models, from 28 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ChronoPhyBench - Frame Sorting (4 Frames)46.5Accuracy (%) on ChronoPhyBench chronological sorting of 4 he100
ChronoPhyBench - Next-State Selection (6 Options)53Accuracy (%) on ChronoPhyBench next-state frame selection wi87.5
ChronoPhyBench - Next-State Selection (3 Options)55Accuracy (%) on ChronoPhyBench next-state frame selection wi85.7
ChronoPhyBench - Frame Sorting (3 Frames)61Accuracy (%) on ChronoPhyBench chronological sorting of 3 he85
OpenCompass Language - Creation (CompassBench 2601)91Score (%)78
OpenCompass Knowledge - Engineering (CompassBench 2601)93Score (%)66
OpenCompass Math - College (CompassBench 2601)74.3Score (%)66
OpenCompass Language - Dialogue (CompassBench 2601)96.4Score (%)64
OpenCompass Reasoning - Academic (CompassBench 2601)39.5Score (%)60
OpenCompass Knowledge - Humanities (CompassBench 2601)90.8Score (%)58
OpenCompass Agent - Tool Use (CompassBench 2601)63.3Score (%)56
OpenCompass LLM - Agent (CompassBench 2601)67.7Score (%)56

Interactive version: theaggregate.ai/model?slug=doubao-seed-1-8-251228 · How It Works · Data refreshed daily, snapshot 2026-09-29.