Expired65% confidenceFactTime unknown

Gemini 3.1 Pro scored 94.3% on the GPQA Diamond test, surpassing OpenAI's o4 and GPT-5.2.

3

Sources

65%

Confidence

Medium-term (~90 days)

Relevance

5/31/2026

First Seen

Valid until: 8/29/2026(expired)

Sources

Gemini 3.1 Pro In-Depth Comparison: 77.1% on ARC-AGI-2 — Is It Really the Best?

bilibili锋芒AI

Related Entities

Gemini 3.1 Promodel GPQA Diamondconcept o4model GPT-5.2model OpenAIcompany

Related Claims

UnverifiedIn the SimpleQA benchmark, Gemini 3.1 Pro leads with a score of 75.6, while DeepSeek V4 Pro scored 57.9.78% similar UnverifiedGemini 3.5 Flash outscored Claude Opus and GPT by 57.9% on the Finance Agent v2 benchmark.74% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/12516

API

curl https://kongchang.com/api/v1/knowledge/claims/12516

MCP

get_claim(id=12516)