Gemini 3.1 Pro Preview (02/26)

Data snapshot 2026-10-26

Overall score

42.0

Awaiting benchmarks (insufficient coverage)

Benchmark coverage

34.6%

9 third-party benchmarks

Context window

—

tokens

Input price

—

per million tokens

Output price

—

per million tokens

Dimension performance

Office

57.2

Coding

34.3

Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation

Coding4 items

Vibe Code Bench32.03

Vibe Code 1–1006.69

Terminal-Bench 4.02.52

ProgramBench0

Office4 items

Tax Eval v272.88

Corporate Finance v264.49

MedCode59.06

Legal Research20.67

Knowledge1 items

MMLU-Pro90.99

Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.