A harder refresh of MMLU intended to keep broad knowledge evaluation useful after the original benchmark became too easy for frontier models.
As of March 2026, Claude Opus 4.5 leads the MMLU-Redux leaderboard with 96.6% , followed by Qwen3.5 397B (94.9%) and Kimi K2.5 (94.5%).
Claude Opus 4.5
Anthropic
Qwen3.5 397B
Alibaba
Kimi K2.5
Moonshot AI
According to BenchLM.ai, Claude Opus 4.5 leads the MMLU-Redux benchmark with a score of 96.6%, followed by Qwen3.5 397B (94.9%) and Kimi K2.5 (94.5%). The top models are clustered within 2.1 points, suggesting this benchmark is nearing saturation for frontier models.
5 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.
Qwen3.6 launch benchmarksVersion
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.
5 AI models have been evaluated on MMLU-Redux on BenchLM.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.