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 2.5 Flash-Lite Preview
Gemini 2.5 Flash-Lite Preview is a proprietary model from Google, released Jul 22, 2025. It ranks #176 of 351 on the LMArena text leaderboard with a rating of 1379. It costs $0.10 per million input tokens and $0.40 per million output tokens, with a 1M-token context window.
- Developer
- Google DeepMind
- Released
- Jul 22, 2025
- Context window
- 1M
- Price in / out, per 1M tokens
- $0.10 / $0.40
- Weights
- Proprietary
- Inputs
- Text, Images, Files, Audio, Video
- Reasoning
- Yes
- Tool use
- Yes
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| MedCodeMedicine | 27.11% | 102 / 107 | $0.1 / $0.4 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1379 | 176 / 351 | 47.4K |
| CodingLMArena | 1373 | 203 / 346 | 6K |
| MathLMArena | 1373 | 191 / 339 | 3K |
| Creative writingLMArena | 1367 | 147 / 349 | 4.2K |
| Instruction followingLMArena | 1367 | 174 / 351 | 8.1K |
| Hard promptsLMArena | 1377 | 180 / 351 | 25.5K |
| Multi-turnLMArena | 1366 | 185 / 349 | 8.1K |
| Long queriesLMArena | 1373 | 178 / 330 | 6.4K |
| ExpertLMArena | 1374 | 178 / 305 | 2.8K |
| Legal and governmentIndustries | 1391 | 170 / 325 | 3.2K |
| Medicine and healthcareIndustries | 1389 | 172 / 325 | 2K |
| Business and financeIndustries | 1367 | 179 / 344 | 9.1K |
| ChineseLanguages | 1404 | 178 / 328 | 3.6K |
| SpanishLanguages | 1396 | 152 / 249 | 1.4K |
| GermanLanguages | 1389 | 134 / 261 | 845 |
| FrenchLanguages | 1388 | 165 / 252 | 841 |
| JapaneseLanguages | 1359 | 119 / 236 | 502 |
| VisionLMArena | 1198 | 95 / 146 | 4.9K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025), Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)).
Compare Gemini 2.5 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 2.5 Flash-Lite Preview?
Gemini 2.5 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 2.5 Flash-Lite Preview cost?
$0.10 per million input tokens and $0.40 per million output tokens, at its provider’s list price.
What is Gemini 2.5 Flash-Lite Preview’s context window?
1M tokens (1,048,576).
How does Gemini 2.5 Flash-Lite Preview rank?
#176 of 351 on LMArena’s text leaderboard, rated 1379 (95% interval 1376–1383) from 47,420 votes, as of Oct 22, 2026.
Is Gemini 2.5 Flash-Lite Preview open source?
No. Gemini 2.5 Flash-Lite Preview is proprietary and served through its provider’s API.