GPQA Diamond (GPQA-D)

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

Top Models on GPQA-D — March 2026

As of March 2026, Claude Opus 4.6 leads the GPQA-D leaderboard with 89.2% , followed by Kimi K2.5 (86.9%) and MiniMax M2.7 (86.2%).

5 modelsKnowledgeCurrentDisplay onlyUpdated April 1, 2026

According to BenchLM.ai, Claude Opus 4.6 leads the GPQA-D benchmark with a score of 89.2%, followed by Kimi K2.5 (86.9%) and MiniMax M2.7 (86.2%). The top models are clustered within 3.0 points, suggesting this benchmark is nearing saturation for frontier models.

5 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.

Trinity-Large-Thinking: Scaling an Open Source Frontier Agent

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.

Leaderboard (5 models)

#1Claude Opus 4.6
89.2%
#2Kimi K2.5
86.9%
#3MiniMax M2.7
86.2%
#4GLM-5
81.6%
#5Trinity-Large-Thinking
76.3%

FAQ

What does GPQA-D measure?

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

Which model scores highest on GPQA-D?

Claude Opus 4.6 by Anthropic currently leads with a score of 89.2% on GPQA-D.

How many models are evaluated on GPQA-D?

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

Last updated: April 1, 2026 · BenchLM version GPQA-D 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.