Advertise here
#71

Gemini 3.1 Pro Preview

Google Release: 2026-02-19 Tested on: 2026-10-01 02:31 google/gemini-3.1-pro-preview::medium
~1.2T total (~20B active)MoEClosedEstimated

Summary

Gemini 3.1 Pro Preview scores 8.4 on AI BENCHY and ranks #71. It has 9.8 reliability, a 89.9% pass rate, $1.585 total cost, and 22.71s average response time.

What makes Gemini 3.1 Pro Preview unique: It stands out most in Domain specific, where it ranks #1, while Agentic is its weakest area at #16.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~1.2T total (~20B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Sparse MoE is documented; counts are estimated.

Parameter source Availability source

Score

8.4

Consistency

9.6

Reliability

9.8

Total Cost (Current Price)

$1.585

Total Output Tokens

102,691

Total Input Tokens

176,208

Input Price

$2.000 / 1M

Output Price

$12.000 / 1M

Cache Read Price

$0.200 / 1M

Cache Write Price

$0.375 / 1M

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 3

Attempt pass rate: 89.9%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

22.71s

Response Time (max): 88.68s

Response Time (total): 386.11s

Wrong answer: 2 Timed out: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#71 Gemini 3.1 Pro Preview

medium
Cost
$0.115
Time
87.2s
Tokens
9,629 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 02:31 Re-test 8.4 9.8 $1.585 Current run
2026-07-16 23:01 New test added 9.2 10.0 $1.361 Compare
2026-06-04 14:04 New test added 9.4 10.0 $1.054 Compare
2026-05-22 00:30 Suite changed 9.3 10.0 $1.006 Compare
2026-04-11 01:44 First recorded run 9.6 N/A $0.578 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 02:31 · Current run69/69 attempts8.49.69.820/231102,691176,208$1.58522.71s
2026-05-22 00:30 · Suite changed60/60 attempts9.310.010.018/20077,3410$1.00620.80s
Difference—-0.9-0.4-0.2+2+1+25350+176208+$0.580+1907ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 60/60 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-08-14 12:51 $2.000 / 1M $12.000 / 1M N/A N/A
2026-10-01 18:33 $2.000 / 1M $12.000 / 1M $0.200 / 1M $0.375 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Gemini 3.1 Pro PreviewmediumvsMuse Glimmer 30BxhighGemini 3.1 Pro PreviewmediumvsInklinghighFree AvailableGemini 3.1 Pro PreviewmediumvsGPT-5 MinimediumGemini 3.1 Pro PreviewmediumvsMuse Spark 1.1highGemini 3.1 Pro PreviewmediumvsQwen3.8 2.4T A95BlowGemini 3.1 Pro PreviewmediumvsDeepSeek V4 Flash 0731highGemini 3.1 Pro PreviewmediumvsQwen3.7 MaxmediumGemini 3.1 Pro PreviewmediumvsGLM 5.2highGemini 3.1 Pro PreviewmediumvsClaude Sonnet 5mediumGemini 3.1 Pro PreviewmediumvsGPT-5.6 Terrahigh

Category Breakdown

Category Score Consistency Tests Correct
Agentic 4.7 1.6
Anti-AI Tricks 10.0 10.0
Coding 7.9 9.9
Combined 9.8 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 10.0 10.0

Compared models