Skip to content
Longterm Wiki
benchmark-result

DeepSeek Models on MMLU-Pro: 75.9

Child of MMLU-Pro

Metadata

Source Tablebenchmark_results
Source IDyKvHaI7BZG
ParentMMLU-Pro
Children
CreatedApr 24, 2026, 6:54 PM
UpdatedApr 24, 2026, 6:54 PM
SyncedApr 24, 2026, 6:54 PM

Record Data

idyKvHaI7BZG
benchmarkId3PM0ZfVJxU
modelIdDeepSeek Models(ai-model)
score75.9
unitpercent
date2024-12-01
sourceUrl
notesDeepSeek-V3 MMLU-Pro benchmark

Source Check Verdicts

confirmed95% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: yKvHaI7BZG

Source Table: benchmark_results

Source ID: yKvHaI7BZG

Parent Thing ID: 3PM0ZfVJxU