Google, proprietary
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite by Google ranks 144th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.8. Its strongest category is multimodal, where it ranks 60th. API pricing starts at $0.25 per million input tokens and $1.50 per million output tokens, with a 1.05M-token context window.
Last verified
Specifications
- Noometry rank
- #144 of 354
- Index score
- 40.8
- Evidence
- Confirmed 38 results
- Provider
Google- Released
- March 3, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 1.05M
- Max output
- 66K
- Input price
- $0.25 / M
- Output price
- $1.50 / M
- Blended price
- $0.56 / M
- Output speed
- 10 tokens/s Kagi
- Value
- #82 of 219
- Knowledge cutoff
- January 2025
- Input
- text, image, video, audio, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 37.8
- Agentic & Tool Use 30.2
- Reasoning 22.9
- Math 40.7
- Knowledge 41.9
- Multimodal 39.4
- Multilingual 52.3
- Instruction Following 72.7
- Long Context 42.5
- Writing & Preference 60.9
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 37.8 | #188 | 4 |
| Agentic & Tool Use | 30.2 | #79 | 1 |
| Reasoning | 22.9 | #186 | 9 |
| Math | 40.7 | #90 | 3 |
| Knowledge | 41.9 | #104 | 4 |
| Multimodal | 39.4 | #60 | 1 |
| Multilingual | 52.3 | #86 | 1 |
| Instruction Following | 72.7 | #131 | 1 |
| Long Context | 42.5 | #122 | 1 |
| Writing & Preference | 60.9 | #94 | 3 |
Strengths and weaknesses
Categories where Gemini 3.1 Flash Lite places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Math | 40.7 | +4.1 | #90 of 327, top 28% |
| Multilingual | 52.3 | +4.9 | #86 of 297, top 29% |
| Writing & Preference | 60.9 | +7.1 | #94 of 312, top 31% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 37.8 | −1.0 | #188 of 340, top 56% |
| Reasoning | 22.9 | −0.7 | #186 of 350, top 54% |
| Agentic & Tool Use | 30.2 | −0.2 | #79 of 154, top 52% |
Closest competitors
The models ranked just above and below Gemini 3.1 Flash Lite. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Kimi K2 (Jul 2025) | #140 | 41.2 | $1 | 201 | Compare |
| Grok-3 mini | #141 | 41.2 | — | 10 | Compare |
| Claude Opus 4.1 | #142 | 41.0 | $30 | — | Compare |
| o1 | #143 | 40.9 | $26.25 | — | Compare |
| Claude Sonnet 4 | #145 | 40.8 | $6 | 31 | Compare |
| Qwen2.5-Max | #146 | 40.7 | — | — | Compare |
| Nemotron 3 Nano 30B A3B | #147 | 40.6 | $0.0875 | — | Compare |
| Granite 4.2 8B | #148 | 40.5 | $0.11 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1256 | #100 of 113, top 89% | LMArena | 2026-10-08 | |
| SciCode | 41.9% | #72 of 121, top 60% | Epoch AI | ||
| WeirdML | 52.2% | #47 of 119, top 40% | Epoch AI | ||
| LMArena Coding | 1400 | #136 of 294, top 47% | LMArena | 2026-10-08 | |
| ALE-Bench | 797.73 | #58 of 105, top 56% | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| DeepResearch Bench | 36.4% | Epoch AI | |||
| DeepResearch Bench | 37.3% | #21 of 24, top 88% | low | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 67.2% | #29 of 99, top 30% | Kagi LLM Benchmark | ||
| NYT Connections (extended) | 8.2% | #88 of 91, top 97% | Lech Mazur benchmarks | ||
| CritPt | 1.1% | #79 of 134, top 59% | Epoch AI | ||
| Chess Puzzles | 20% | high | Epoch AI | 2026-08-06 | |
| Chess Puzzles | 25% | #43 of 129, top 34% | low | Epoch AI | 2026-08-06 |
| Chess Puzzles | 24% | minimal | Epoch AI | 2026-08-06 | |
| EnigmaEval | 3% | #28 of 38, top 74% | Epoch AI | ||
| Thematic Generalization | 63.3% | #11 of 23, top 48% | Lech Mazur benchmarks | ||
| LMArena Hard Prompts | 1407 | #120 of 297, top 41% | LMArena | 2026-10-08 | |
| DTBench | 76.8% | #83 of 151, top 55% | high | Epoch AI | |
| LMCA | 35% | #62 of 125, top 50% | high | Epoch AI | |
| Epoch Capabilities Index | 144.47 | #85 of 213, top 40% | Epoch AI | 2026-03-03 | |
| ForecastBench | 54.4 | #67 of 72, top 94% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | #62 of 81, top 77% | high | Epoch AI | 2026-08-30 |
| FrontierMath (Tiers 1-3) | 22.5% | low | Epoch AI | 2026-08-30 | |
| FrontierMath (Tiers 1-3) | 21.4% | minimal | Epoch AI | 2026-08-28 | |
| OTIS Mock AIME 2024-2025 | 80% | #80 of 173, top 47% | high | Epoch AI | 2026-08-06 |
| OTIS Mock AIME 2024-2025 | 44.4% | low | Epoch AI | 2026-08-06 | |
| OTIS Mock AIME 2024-2025 | 37.8% | minimal | Epoch AI | 2026-08-06 | |
| LMArena Math | 1428 | #90 of 285, top 32% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 81.8% | #77 of 186, top 42% | high | Epoch AI | 2026-08-06 |
| GPQA Diamond | 74.2% | low | Epoch AI | 2026-08-06 | |
| GPQA Diamond | 73.7% | minimal | Epoch AI | 2026-08-06 | |
| Humanity's Last Exam | 8.6% | #25 of 41, top 61% | Epoch AI | ||
| Vectara Hallucination Rate (lower is better) | 8.2% | #36 of 96, top 38% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1398 | #123 of 273, top 46% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1240 | #64 of 122, top 53% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1411 | #86 of 297, top 29% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1461 | #90 of 285, top 32% | LMArena | 2026-10-08 | |
| LMArena French | 1424 | #97 of 223, top 44% | LMArena | 2026-10-08 | |
| LMArena German | 1429 | #66 of 231, top 29% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1413 | #46 of 211, top 22% | LMArena | 2026-10-08 | |
| LMArena Korean | 1392 | #64 of 213, top 31% | LMArena | 2026-10-08 | |
| LMArena Russian | 1420 | #81 of 283, top 29% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1421 | #89 of 226, top 40% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1377 | #124 of 298, top 42% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1394 | #122 of 291, top 42% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1416 | #103 of 297, top 35% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1401 | #79 of 295, top 27% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1417 | #98 of 295, top 34% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| $0.25 | $1.50 | $0.025 | 2026-10-10 | |
| openrouter | $0.25 | $1.50 | $0.025 | 2026-10-10 |
| vertex | $0.25 | $1.50 | $0.025 | 2026-10-10 |
Compare Gemini 3.1 Flash Lite
- Gemini 3.1 Flash Lite vs Gemini 2.5 Flash-Lite
- Gemini 3.1 Flash Lite vs o1
- Gemini 3.1 Flash Lite vs Claude Sonnet 4
- Gemini 3.1 Flash Lite vs Claude Opus 4.1
- Gemini 3.1 Flash Lite vs Qwen2.5-Max
- Gemini 3.1 Flash Lite vs Grok-3 mini
- Gemini 3.1 Flash Lite vs Nemotron 3 Nano 30B A3B
- Gemini 3.1 Flash Lite vs GPT-6 Astra
- Gemini 3.1 Flash Lite vs Claude Fable 5.1
- Gemini 3.1 Flash Lite vs Kimi K3
- Gemini 3.1 Flash Lite vs Grok 4.6
- Gemini 3.1 Flash Lite vs Qwen3.8 Max
- Gemini 3.1 Flash Lite vs GLM-5.3
- Gemini 3.1 Flash Lite vs Muse Spark 1.3
Other Google models
Frequently asked questions
How good is Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite by Google ranks 144th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.8. Its strongest category is multimodal, where it ranks 60th. API pricing starts at $0.25 per million input tokens and $1.50 per million output tokens, with a 1.05M-token context window.
How much does Gemini 3.1 Flash Lite cost?
Gemini 3.1 Flash Lite costs $0.25 per million input tokens and $1.50 per million output tokens on Google's own API, with cached input at $0.025.
What is Gemini 3.1 Flash Lite's context window?
Gemini 3.1 Flash Lite accepts up to 1.05M tokens of input and can write up to 66K tokens in one response.
Is Gemini 3.1 Flash Lite open source?
No. Gemini 3.1 Flash Lite is proprietary and available only through Google's API and partner platforms.
How fast is Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite generated about 10 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Gemini 3.1 Flash Lite's strengths and weaknesses?
Relative to other ranked models, Gemini 3.1 Flash Lite places best in math, multilingual, writing & preference and lowest in coding, reasoning, agentic & tool use.
What is Gemini 3.1 Flash Lite best at?
Its best category is multimodal, where it ranks 60th on Noometry.