Benchmark

MultiChallenge

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

Released
2025-01-29
Categories
instruction_following
Openness
unknown
Source
model_reports
Reported scores
1

Reported scores

model_reports

ModelOrganizationReported valueReportedEvidence
Qwen3.5-397B-A17BQwen67.62026-02-16evidence

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.