Skip to content
Longterm Wiki
benchmark-result

Claude Opus 4.5 on MMLU-Pro: 89.5

Child of MMLU-Pro

Metadata

Source Tablebenchmark_results
Source ID0x0bVn7TBv
Source URLautomatio.ai/models/claude-opus-4-5
ParentMMLU-Pro
Children
CreatedApr 24, 2026, 7:48 PM
UpdatedApr 24, 2026, 7:48 PM
SyncedApr 24, 2026, 7:48 PM

Record Data

id0x0bVn7TBv
benchmarkId3PM0ZfVJxU
modelIdClaude Opus 4.5(ai-model)
score89.5
unitpercent
date2025-11-24
sourceUrlautomatio.ai/models/claude-opus-4-5
notesMMLU-Pro - enhanced MMLU with harder 10-option multiple choice format

Source Check Verdicts

confirmed99% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: 0x0bVn7TBv

Source Table: benchmark_results

Source ID: 0x0bVn7TBv

Parent Thing ID: 3PM0ZfVJxU