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 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is a proprietary model from Google, released Jul 21, 2026. It ranks #88 of 351 on the LMArena text leaderboard with a rating of 1435. It costs $0.30 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.
- Developer
- Google DeepMind
- Released
- Jul 21, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $0.30 / $2.50
- Weights
- Proprietary
- Inputs
- Text, Images, Video, Files, Audio
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Jul 21, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 75.00% | 42 / 85 | $0.31 | |
| Vibe Code BenchCoding | 37.16% | 70 / 115 | $0.83 | |
| LiveCodeBenchCoding | 79.01% | 75 / 143 | $0.3 / $2.5 | |
| Tax Agent BenchFinance | 7.25% | 67 / 76 | $0.08 | |
| Legal Research BenchLaw | 13.94% | 72 / 85 | $0.12 | |
| MedCodeMedicine | 43.49% | 44 / 107 | $0.3 / $2.5 | |
| GPQA DiamondReasoning | 83.84% | 56 / 138 | $0.3 / $2.5 | |
| MMLU-ProReasoning | 85.84% | 54 / 138 | $0.3 / $2.5 | |
| MMMUReasoning | 83.58% | 30 / 93 | $0.3 / $2.5 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1435 | 88 / 351 | 35.8K |
| CodingLMArena | 1453 | 99 / 346 | 9.9K |
| MathLMArena | 1435 | 94 / 339 | 1.6K |
| Creative writingLMArena | 1421 | 68 / 349 | 7.5K |
| Instruction followingLMArena | 1419 | 90 / 351 | 12.9K |
| Hard promptsLMArena | 1441 | 95 / 351 | 23.8K |
| Multi-turnLMArena | 1445 | 75 / 349 | 5.9K |
| Long queriesLMArena | 1435 | 87 / 330 | 17.1K |
| ExpertLMArena | 1433 | 112 / 305 | 4.2K |
| Legal and governmentIndustries | 1431 | 106 / 325 | 3.1K |
| Medicine and healthcareIndustries | 1438 | 101 / 325 | 2.6K |
| Business and financeIndustries | 1423 | 98 / 344 | 6.6K |
| ChineseLanguages | 1467 | 92 / 328 | 2.7K |
| SpanishLanguages | 1442 | 80 / 249 | 963 |
| GermanLanguages | 1454 | 50 / 261 | 656 |
| FrenchLanguages | 1451 | 85 / 252 | 1.1K |
| JapaneseLanguages | 1426 | 46 / 236 | 590 |
| WebDevLMArena | 1434 | 87 / 124 | 237 |
| VisionLMArena | 1269 | 45 / 146 | 9.2K |
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 3.5 Flash-Lite
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 3.5 Flash-Lite?
Gemini 3.5 Flash-Lite is made by Google DeepMind, founded 2010 (DeepMind), merged with Google Brain in 2023 and based in London.
How much does Gemini 3.5 Flash-Lite cost?
$0.30 per million input tokens and $2.50 per million output tokens, at its provider’s list price.
What is Gemini 3.5 Flash-Lite’s context window?
1M tokens (1,048,576).
How does Gemini 3.5 Flash-Lite rank?
#88 of 351 on LMArena’s text leaderboard, rated 1435 (95% interval 1431–1439) from 35,829 votes, as of Oct 22, 2026.
Is Gemini 3.5 Flash-Lite open source?
No. Gemini 3.5 Flash-Lite is proprietary and served through its provider’s API.