Skip to content

Gemini 3.1 Pro

GoogleProprietaryReasoningProvisionalReleased Feb 19, 2026
Compare with Claude Sonnet 5Source scores ↗
Overall score
64.7
Rank 38 of 222 · 55.0–74.5
Context window
1M
1,000,000 tokens
Price per 1M tokens
$2.00 in · $12.00 out
✓ Verified on Google's pricing page
Blended price
$4.50
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Multimodal#1780.1
  2. 2Coding#6878.1
  3. 3Knowledge#2677.1
  4. 4Agentic & tool use#7369.0
  5. 5Math65.0
  6. 6Reasoning58.2
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (24)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Multimodal

Design Arena Website1254#41 of 91
MMMU-Pro83.9#1 of 48
CharXiv80.2#28 of 42
ParseBench69.14#16 of 37
SimpleVQA72.4#7 of 17
ERQA69.4#7 of 16
ScreenSpot Pro84.4#5 of 15
ZeroBench29.0#4 of 8
MedXpertQA (MM)81.3#1 of 8

Agentic & tool use

Gert Labs56.87#14 of 52
MazeBench1#13 of 42
Claw-Eval57.8#25 of 36
DeepSearchQA69.7#18 of 20
ResearchClawBench13.3#18 of 19

Coding

React Native Evals78.9#7 of 15
PostTrainBench v1.122.0#14 of 15
LiveCodeBench Pro82.9#2 of 6

Knowledge

HLE w/o tools45.4#11 of 43
HealthBench Hard20.6#10 of 12
MedXpertQA (Text)71.5#1 of 5

Reasoning

ARC-AGI-277.1#17 of 41
ARC-AGI-30.4#15 of 22

Math

FrontierMath v2 (Tiers 1-3)59.649#33 of 64
FrontierMath v2 (Tier 4)26.829#30 of 51

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
✓ Official (Google)
checked Oct 17, 2026 · gemini-3.1-pro-preview
$2.00$12.00—
BenchLM list price$2.00$12.00$0.20

Paid tier, prompts up to 200K tokens. Several prices change on Dec 1, 2026 / Jan 1, 2027.

Google's Gemini Developer API pricing page lists gemini-3.1-pro-preview at $2.00 input / $0.20 cached input / $12.00 output per million tokens for prompts up to 200K tokens, rising to $4.00 / $0.40 / $18.00 above 200K. The gemini-3.1-pro-preview-customtools endpoint has the same pricing. Batch and Flex input/output rates are $1.00 / $6.00 through 200K tokens and $2.00 / $9.00 above 200K, with cached input at Standard rates; Priority rates are $3.60 / $21.60 through 200K and $7.20 / $32.40 above 200K, with cached input at $0.36 / $0.72.

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.

Related models

Similar score