Skip to content
Longterm Wiki
benchmark-result

Claude Opus 4.6 on GSM8K: 98.4

Child of GSM8K

Metadata

Source Tablebenchmark_results
Source IDHMgqZsW2qE
Source URLautomatio.ai/models/claude-opus-4-6
ParentGSM8K
Children
CreatedApr 24, 2026, 7:52 PM
UpdatedApr 24, 2026, 7:52 PM
SyncedApr 24, 2026, 7:52 PM

Record Data

idHMgqZsW2qE
benchmarkIdfjjBrOI3p2
modelIdClaude Opus 4.6(ai-model)
score98.4
unitpercent
date2026-02-05
sourceUrlautomatio.ai/models/claude-opus-4-6
notes

Source Check Verdicts

confirmed99% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: HMgqZsW2qE

Source Table: benchmark_results

Source ID: HMgqZsW2qE

Parent Thing ID: fjjBrOI3p2