Skip to main content

GPQA Diamond (GPQA-D)

A display-only GPQA Diamond reference from provider comparison charts.

Benchmark score on GPQA-D — May 13, 2026

BenchLM mirrors the published score view for GPQA-D. Gemini 3.1 Pro leads the public snapshot at 94.3% , followed by Claude Opus 4.7 (Adaptive) (94.2%) and GPT-5.5 (93.6%). BenchLM does not use these results to rank models overall.

25 modelsKnowledgeCurrentDisplay onlyUpdated May 13, 2026

The published GPQA-D snapshot is tightly clustered at the top: Gemini 3.1 Pro sits at 94.3%, while the third row is only 0.7 points behind. The broader top-10 spread is 5.2 points, so many of the published scores sit in a relatively narrow band.

25 models have been evaluated on GPQA-D. The benchmark falls in the Knowledge category. This category carries a 12% weight in BenchLM.ai's overall scoring system. GPQA-D is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About GPQA-D

Year

2026

Tasks

Graduate-level science questions

Format

Multiple choice questions

Difficulty

Graduate level

BenchLM stores GPQA-D separately from the standardized GPQA row when providers publish exact chart values that should not overwrite the core weighted benchmark.

BenchLM freshness & provenance

Version

GPQA-D 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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.

Benchmark score table (25 models)

1
94.3%
2
94.2%
3
93.6%
4
92.8%
5
90.5%
6
90.1%
7
89.9%
8
89.5%
9
89.2%
10
89.1%
11
88.5%
12
88.1%
13
87.6%
14
87.4%
15
87.2%
16
87.0%
17
86.2%
18
86.0%
19
76.3%
20
72.9%
22
71.2%
23
71.0%
24
63.3%
25
57.3%

FAQ

What does GPQA-D measure?

A display-only GPQA Diamond reference from provider comparison charts.

Which model scores highest on GPQA-D?

Gemini 3.1 Pro by Google currently leads with a score of 94.3% on GPQA-D.

How many models are evaluated on GPQA-D?

25 AI models have been evaluated on GPQA-D on BenchLM.

Last updated: May 13, 2026 · BenchLM version GPQA-D 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.