← leaderboard
Gemini 3.1 Pro
NOT COOKEDGoogle · google/gemini-3.1-pro-preview · verdict as of 2026-08-10
Daily test history (90 days, baseline band = trailing mean ± 2σ)
Structured Extraction
NOT COOKED
Math & Reasoning
NOT COOKED
Code Generation
NOT COOKED
Instruction Following
NOT COOKED
Report Analysis
NOT COOKED
Summarization
NOT COOKED
Customer Service
NOT COOKED
Creative Writing
no data
Game Design
NOT COOKED
Web Design
NOT COOKED
Serving providers (last 30 days)
striped = multiple providers served this model that day (hover for detail)
Public benchmarks overall 87.9
MMLU-Pro
91.2
GPQA Diamond
94.3
SWE-bench Verified
80.6
LMArena Elo
1486
AIME 2025
—
retrieved 2026-07-03 from public sources — see methodology
Recent samples (latest run, one per test case)
No samples from the latest run.