AI Benchmark Model

Gemini 3.1 Pro Preview

Benchmark scores, pricing, speed, and model comparisons for Gemini 3.1 Pro Preview.

Key scores

Intelligence57.2Index score
Coding55.5Index score
Speed139.4Tokens/sec
Blended Cost$4.50Per 1M tokens

Gemini 3.1 Pro Preview is an artificial intelligence model developed by Google, released on February 19, 2026. In performance evaluations, the model achieved an intelligence index of 57.2 and a coding index of 55.5. Benchmark results include a GPQA score of 0.941, an HLE score of 0.447, a SciCode score of 0.589, an IFBench score of 0.771, an LCR score of 0.727, a TerminalBench Hard score of 0.538, and a TAU2 score of 0.956. Regarding operational metrics, the model demonstrates an output speed of 123.203 tokens per second with a time to first token of 18.613 seconds. Pricing for the model is set at $2.00 per 1M input tokens and $12.00 per 1M output tokens, resulting in a blended rate of $4.50 per 1M tokens.

Benchmark results

7 tracked benchmark rows for Gemini 3.1 Pro Preview.

TAU2 Other
95.6%
GPQA Reasoning
94.1%
IFBench Other
77.1%
LCR Other
72.7%
SciCode Other
58.9%
TerminalBench Hard Other
53.8%
HLE Other
44.7%

Comments (0)

No comments yet

Be the first to share your thoughts!