← Gemini 3.1 Pro · API · High thinking
Evidenceacceptedindependent_lab
GPQA Diamond
Artificial Analysis — GPQA Diamond (Gemini 3.1 Pro Preview)
ev_2026_07_gem31pro_aa_gpqa
Result
94.1%
Confidence A
- Tested
- 2026-07-11
- Runs
- 1
Configuration
How it was measured
- Exact model
- gemini-3.1-pro-preview
- Reasoning
- high
- Agent harness
- none
- Tool access
- none (closed-book scientific QA)
- Prompting
- Artificial Analysis standard GPQA Diamond protocol
PRIMARY INT — Artificial Analysis GPQA Diamond. AA leaderboard summary ties Gemini 3.1 Pro Preview with GPT-5.6 Sol max at ~94.1%.
Caveats
Known limitations
- GPQA near-saturated at frontier; use peer comparison not absolute %.
- High/thinking config — not Flash.
Weighting
Evidence weight factors
The engine weights each evidence row by these factors (0–1) when fusing scores — higher is more trusted.
relevance0.95
quality1.00
recency1.00
health0.70
comparability0.90
reliability0.85
Benchmark
GPQA Diamond
Graduate-level science questions (biology, physics, chemistry) designed to be Google-proof; Diamond is the hardest subset where PhD experts score ~65%.
Benchmark source →