Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
Gemini 3.1 Flash-Lite Preview
Gemini 3.1 Flash-Lite Preview is a proprietary model from Google, released May 7, 2026. It ranks #131 of 351 on the LMArena text leaderboard with a rating of 1416. It costs $0.25 per million input tokens and $1.50 per million output tokens, with a 1M-token context window.
- Developer
- Google DeepMind
- Released
- May 7, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $0.25 / $1.50
- Weights
- Proprietary
- Inputs
- Text, Images, Video, Files, Audio
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Mar 3, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 62.80% | 72 / 85 | $0.11 | |
| Vibe Code BenchCoding | 0.00% | 112 / 115 | $0.51 | |
| LiveCodeBenchCoding | 80.12% | 71 / 143 | $0.25 / $1.5 | |
| Tax Agent BenchFinance | 3.11% | 74 / 76 | $0.01 | |
| Legal Research BenchLaw | 3.37% | 81 / 85 | $0.01 | |
| MedCodeMedicine | 47.60% | 32 / 107 | $0.25 / $1.5 | |
| GPQA DiamondReasoning | 81.06% | 66 / 138 | $0.25 / $1.5 | |
| MMLU-ProReasoning | 86.24% | 45 / 138 | $0.25 / $1.5 | |
| AIMEReasoning | 83.33% | 43 / 96 | $0.25 / $1.5 | |
| MMMUReasoning | 82.49% | 37 / 93 | $0.25 / $1.5 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1416 | 131 / 351 | 64.2K |
| CodingLMArena | 1400 | 175 / 346 | 17.9K |
| MathLMArena | 1428 | 107 / 339 | 3.6K |
| Creative writingLMArena | 1401 | 99 / 349 | 10.6K |
| Instruction followingLMArena | 1377 | 161 / 351 | 21.5K |
| Hard promptsLMArena | 1407 | 154 / 351 | 41.6K |
| Multi-turnLMArena | 1417 | 121 / 349 | 11.6K |
| Long queriesLMArena | 1394 | 158 / 330 | 27.2K |
| ExpertLMArena | 1399 | 158 / 305 | 6.2K |
| Legal and governmentIndustries | 1418 | 134 / 325 | 5K |
| Medicine and healthcareIndustries | 1427 | 122 / 325 | 4.8K |
| Business and financeIndustries | 1389 | 157 / 344 | 12.6K |
| ChineseLanguages | 1460 | 108 / 328 | 4.2K |
| SpanishLanguages | 1421 | 113 / 249 | 2K |
| GermanLanguages | 1430 | 83 / 261 | 1K |
| FrenchLanguages | 1424 | 130 / 252 | 2.1K |
| JapaneseLanguages | 1413 | 62 / 236 | 647 |
| WebDevLMArena | 1256 | 135 / 124 | 14.4K |
| VisionLMArena | 1240 | 73 / 146 | 27.7K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Gemini 3.1 Flash-Lite Preview
Google DeepMind
Google’s AI lab, behind Gemini and the open Gemma family, with very long context and native multimodality. Founded 2010 (DeepMind), merged with Google Brain in 2023, based in London. deepmind.google
Questions
Who makes Gemini 3.1 Flash-Lite Preview?
Gemini 3.1 Flash-Lite Preview is made by Google DeepMind, founded 2010 (DeepMind), merged with Google Brain in 2023 and based in London.
How much does Gemini 3.1 Flash-Lite Preview cost?
$0.25 per million input tokens and $1.50 per million output tokens, at its provider’s list price.
What is Gemini 3.1 Flash-Lite Preview’s context window?
1M tokens (1,048,576).
How does Gemini 3.1 Flash-Lite Preview rank?
#131 of 351 on LMArena’s text leaderboard, rated 1416 (95% interval 1412–1419) from 64,209 votes, as of Oct 22, 2026.
Is Gemini 3.1 Flash-Lite Preview open source?
No. Gemini 3.1 Flash-Lite Preview is proprietary and served through its provider’s API.