Model results

GPQA Diamond

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Use as a compact reference for expert-written science questions, alongside evidence that matches the scientific work you intend to do.

Original GPQA Diamond subset. Preserve prompt, answer extraction, tools, sampling and aggregation. Keep main, extended and third-party corrected subsets separate.. Imported groups below may use different protocols; this review does not certify each run. The static 198-question subset has limited statistical power and exposure risk. Its expert filtering does not make it representative of scientific practice. A Google-proof collection process does not prove present-day contamination resistance.

Publisher results GPQA paper

← All evaluation groups

GPQA Diamond

Source: Epoch AI Benchmarking Hub
Version: Not reported
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Epoch AI run · task v1 · effort 32K · result date not supplied

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

#1Claude Opus 4.6
anthropic/claude-opus-4-6
90.5%
View modelEvidence independent
#2Claude Sonnet 4.6
anthropic/claude-sonnet-4-6
87.4%
View modelEvidence independent
#3Claude Opus 4.5
anthropic/claude-opus-4-5
86%
View modelEvidence independent
#4Claude Sonnet 4.5
anthropic/claude-sonnet-4-5
81.7%
View modelEvidence independent
#5Claude Sonnet 4
anthropic/claude-sonnet-4
78.3%
View modelEvidence independent
#6Claude Haiku 4.5
anthropic/claude-haiku-4-5
71.2%
View modelEvidence independent