A harder refresh of MMLU intended to keep broad knowledge evaluation useful after the original benchmark became too easy for frontier models.
BenchLM mirrors the published score view for MMLU-Redux. Claude Opus 4.5 leads the public snapshot at 96.6% , followed by Qwen3.5 397B (94.9%) and Qwen3.6 Plus (94.5%). BenchLM does not use these results to rank models overall.
Claude Opus 4.5
Anthropic
Qwen3.5 397B
Alibaba
Qwen3.6 Plus
Alibaba
The published MMLU-Redux snapshot is tightly clustered at the top: Claude Opus 4.5 sits at 96.6%, while the third row is only 2.1 points behind. The broader top-10 spread is 2.1 points, so many of the published scores sit in a relatively narrow band.
3 models have been evaluated on MMLU-Redux. The benchmark falls in the Knowledge category. This category carries a 12% weight in BenchLM.ai's overall scoring system. MMLU-Redux is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Broad academic QA
Format
Multiple choice questions
Difficulty
Advanced general knowledge
MMLU-Redux is useful when MMLU itself has largely saturated. It acts as a broader knowledge sanity check with fresher or harder questions intended to preserve separation among strong general-purpose models.
Version
MMLU-Redux 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A harder refresh of MMLU intended to keep broad knowledge evaluation useful after the original benchmark became too easy for frontier models.
Claude Opus 4.5 by Anthropic currently leads with a score of 96.6% on MMLU-Redux.
3 AI models have been evaluated on MMLU-Redux on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.