#4 Gemini 3.1 Pro Preview
medium- Cost
- $0.115
- Time
- 87.2s
- Tokens
- 9,629 tok
Google
Release: 2026-02-19
Tested on: 2026-06-04 14:04
google/gemini-3.1-pro-preview::medium
~1.2T total (~20B active)MoEClosedEstimated Summary
Gemini 3.1 Pro Preview scores 9.4 on AI BENCHY and ranks #4. It has 10.0 reliability, a 90.5% pass rate, $1.054 total cost, and 20.14s average response time.
What makes Gemini 3.1 Pro Preview unique: It stands out most in Domain specific, where it ranks #2, while Coding is its weakest area at #12. It is one of the highest-ranked models overall.
Model facts
Researched on 2026-08-12
- 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.
9.4
Consistency
10.0
10.0
$1.054
Total Output Tokens
80,873
Total Input Tokens
41,617
Input Price
$2.000 / 1M
Output Price
$12.000 / 1M
Flaky tests
0
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:51 Re-test | 9.2 | 10.0 | $1.352 | Compare | |
| 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 | Current run | |
| 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
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-06-04 14:04 · New test added | 63/63 attempts | 9.4 | 10.0 | 10.0 | 19/21 | 0 | 80,873 | 41,617 | $1.054 | 20.14s |
| 2026-04-11 01:44 · First recorded run | 54/54 attempts | 9.6 | 10.0 | N/A | 17/18 | 0 | 42,474 | 0 | $0.578 | 15.96s |
| Difference | — | -0.2 | 0.0 | +2 | 0 | +38399 | +41617 | +$0.476 | +4181ms |
Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 54/54 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 |
|---|---|---|
| 2026-06-04 14:42 | $2.000 / 1M | $12.000 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Gemini 3.1 Pro PreviewmediumvsGrok 4.6highGemini 3.1 Pro PreviewmediumvsGemini 3.7 FlashlowGemini 3.1 Pro PreviewmediumvsGPT-5.5lowGemini 3.1 Pro PreviewmediumvsClaude Opus 5highGemini 3.1 Pro PreviewmediumvsGPT-5.6 SolhighGemini 3.1 Pro PreviewmediumvsClaude Opus 5mediumGemini 3.1 Pro PreviewmediumvsGPT-5.6 SolmediumGemini 3.1 Pro PreviewmediumvsSeed 2.1 TurbolowGemini 3.1 Pro PreviewmediumvsGemini 3.7 FlashmediumGemini 3.1 Pro PreviewmediumvsQwen3.7 Maxmedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 7.9 | 9.9 | |
| Combined | 9.5 | 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 |