#22 Gemini 3.1 Flash Lite
medium- Cost
- $0.003
- Time
- 5.3s
- Tokens
- 1,754 tok
Google
Release: 2026-05-08
Tested on: 2026-05-08 12:01
google/gemini-3.1-flash-lite::medium
Summary
Gemini 3.1 Flash Lite scores 8.2 on AI BENCHY and ranks #22. It has 10.0 reliability, a 75.9% pass rate, $0.056 total cost, and 3.14s average response time.
What makes Gemini 3.1 Flash Lite unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Identity note
Google: Gemini 3.1 Flash Lite Preview was the preview version of Gemini 3.1 Flash Lite.
8.2
Consistency
9.1
10.0
$0.056
Total Output Tokens
32,369
Total Input Tokens
0
Input Price
$0.250 / 1M
Output Price
$1.500 / 1M
Flaky tests
2
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 |
|---|---|---|---|---|---|
| 2026-07-16 22:52 New test added | 7.3 | 10.0 | $0.117 | Compare | |
| 2026-06-04 14:00 New test added | 7.5 | 10.0 | $0.071 | Compare | |
| 2026-05-22 00:27 Suite changed | 7.7 | 10.0 | $0.065 | Compare | |
| 2026-05-08 12:01 Initial run | 8.2 | 10.0 | $0.056 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-08 12:01 · Initial run | 18/18 tests · 54/54 attempts | 8.2 | 9.1 | 10.0 | 13/18 | 2 | 32,369 | 0 | $0.056 | 3.14s |
| 2026-07-16 22:52 · New test added | 22/22 tests · 66/66 attempts | 7.3 | 9.2 | 10.0 | 13/22 | 2 | 60,298 | 104,918 | $0.117 | 4.27s |
| Difference | — | +0.9 | -0.1 | 0.0 | 0 | 0 | -27929 | -104918 | -$0.061 | -1132ms |
Benchmark coverage differs: 18/18 tests · 54/54 attempts (Target: 3 repeats per test) versus 22/22 tests · 66/66 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.
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 Flash LitemediumvsDeepSeek V4 Flash 0731mediumGemini 3.1 Flash LitemediumvsQwen3.7 FlashlowGemini 3.1 Flash LitemediumvsGemini 3.1 Flash Lite PreviewmediumGemini 3.1 Flash LitemediumvsClaude Opus 4.8noneGemini 3.1 Flash LitemediumvsClaude Sonnet 4.6noneGemini 3.1 Flash LitemediumvsStep 3.7 FlashlowGemini 3.1 Flash LitemediumvsKAT-Coder-Pro V2.5lowGemini 3.1 Flash LitemediumvsKimi K2.6mediumGemini 3.1 Flash LitemediumvsGemini 3 Flash PreviewlowGemini 3.1 Flash LitemediumvsKAT-Coder-Pro V2.5high
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 9.1 | 10.0 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 9.9 | 10.0 | |
| Puzzle Solving | 7.6 | 7.2 | |
| Tool Calling | 10.0 | 10.0 |