New

Work in progress: Agents Directory has just launched. Stay tuned, more content is on the way.

Gemini 3.1 Pro Preview

Google's preview-tier Pro model, strong on reasoning before the 3.5 Flash refresh.

Capabilities:

Input

Text input
Image input (vision)
File input (PDF)
Audio input
Video input

Output

Text output
Image output
Audio output

Benchmark scores:

BenchmarkRankScore

Artificial Analysis Intelligence Index
Rank#5 of 19
Score57.2
FrontierCode Main
Rank#6 of 12
Score16.7%
FrontierCode Diamond
Rank#4 of 11
Score4.7%

Gemini 3.1 Pro Preview on Artificial Analysis Intelligence Index

57.2

The most-cited composite intelligence score: a 0–100 index combining knowledge, reasoning, math, coding, and agentic evaluations (GPQA Diamond, HLE, IFBench, SciCode, Terminal-Bench Hard, τ²-Bench, and more). Higher is better.

Gemini 3.1 Pro Preview scores 57.2, #5 of 19 tracked models.
Claude Fable 5 leads at 64.9. The group median is 53.2.

vs. top models

Full interactive leaderboard on our Artificial Analysis Intelligence Index page.

Source: artificialanalysis.ai · Updated June 2026

Gemini 3.1 Pro Preview on FrontierCode Main

16.7%

Cognition's test of whether a model writes code maintainers would actually merge, not just code that passes tests. Main is the 100 hardest of 150 tasks. Higher is better.

Gemini 3.1 Pro Preview scores 16.7%, #6 of 12 tracked models.
Claude Fable 5 leads at 46.3%. The group median is 16.35%.

vs. top models

Full interactive leaderboard on our FrontierCode Main page.

Source: cognition.ai · Updated June 2026

Gemini 3.1 Pro Preview on FrontierCode Diamond

4.7%

The 50 hardest FrontierCode tasks: the toughest production-code problems, graded on whether maintainers would merge the patch. Scores stay low by design. Higher is better.

Gemini 3.1 Pro Preview scores 4.7%, #4 of 11 tracked models.
Claude Opus 4.8 leads at 13.4%. The group median is 3.8%.

Source: cognition.ai · Updated June 2026

Pricing & availability:

OpenRouter
$2 / $12 per M

Strengths:

reasoninglong contextvalue

Sources:

OpenRouter

Share:

Details:

Provider
Google DeepMind
Context window
1.049M
Input price
$2/M
Output price
$12/M
Open weights
No
Released
May 2026