Benchmark Radar™
Star —

MultiChallenge Benchmark

Explore score history ↗

Multi-turn instruction retention, graded by an LLM judge.

Released
2025-01-29
Evaluates
reasoning
Openness
unknown
Importer
Model reports

MultiChallenge paper

MultiChallenge results and reported scores

Reported benchmark scores · Model reports

Reported scores: 3

ModelOrganizationReported valueReportedEvidence
Seed2.0 LiteByteDance63.22026-02-14evidence
Seed2.0 MiniByteDance61.12026-02-14evidence
Seed2.0 ProByteDance68.32026-02-14evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite MultiChallenge?

Related reasoning benchmarks