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 Pro Preview
Gemini 3.1 Pro Preview is a proprietary model from Google, released Feb 19, 2026. It ranks #19 of 351 on the LMArena text leaderboard with a rating of 1480. It costs $2 per million input tokens and $12 per million output tokens, with a 1M-token context window.
- Developer
- Google DeepMind
- Released
- Feb 19, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $2 / $12
- Weights
- Proprietary
- Inputs
- Audio, Files, Images, Text, Video
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Feb 6, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Terminal-Bench 4.0Coding | 2.52% | 49 / 55 | $4.11 | |
| SWE-benchCoding | 78.80% | 28 / 85 | $0.78 | |
| Vibe Code BenchCoding | 32.03% | 72 / 115 | $3.83 | |
| LiveCodeBenchCoding | 88.48% | 6 / 143 | $2 / $12 | |
| Tax Agent BenchFinance | 9.29% | 62 / 76 | $0.30 | |
| Legal Research BenchLaw | 20.67% | 62 / 85 | $1.10 | |
| MedCodeMedicine | 59.06% | 2 / 107 | $2 / $12 | |
| MedQAMedicine | 96.37% | 3 / 92 | $2 / $12 | |
| GPQA DiamondReasoning | 95.45% | 1 / 138 | $2 / $12 | |
| MMLU-ProReasoning | 90.99% | 4 / 138 | $2 / $12 | |
| AIMEReasoning | 98.13% | 1 / 96 | $2 / $12 | |
| MMMUReasoning | 88.21% | 10 / 93 | $2 / $12 | |
| Terminal-Bench ScienceReasoning | 1.43% | 35 / 42 | $5.91 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1480 | 19 / 351 | 130.8K |
| CodingLMArena | 1484 | 48 / 346 | 35.8K |
| MathLMArena | 1486 | 28 / 339 | 6.8K |
| Creative writingLMArena | 1482 | 14 / 349 | 24.4K |
| Instruction followingLMArena | 1466 | 35 / 351 | 44.8K |
| Hard promptsLMArena | 1485 | 30 / 351 | 84.9K |
| Multi-turnLMArena | 1487 | 17 / 349 | 22.1K |
| Long queriesLMArena | 1482 | 24 / 330 | 57.8K |
| ExpertLMArena | 1483 | 45 / 305 | 13.6K |
| Legal and governmentIndustries | 1487 | 22 / 325 | 10.7K |
| Medicine and healthcareIndustries | 1487 | 21 / 325 | 9.8K |
| Business and financeIndustries | 1459 | 33 / 344 | 25.3K |
| ChineseLanguages | 1529 | 23 / 328 | 9.1K |
| SpanishLanguages | 1480 | 14 / 249 | 4.2K |
| GermanLanguages | 1490 | 15 / 261 | 2.2K |
| FrenchLanguages | 1488 | 27 / 252 | 4.3K |
| JapaneseLanguages | 1493 | 12 / 236 | 1.6K |
| WebDevLMArena | 1447 | 78 / 124 | 24.2K |
| VisionLMArena | 1296 | 22 / 146 | 47.1K |
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 Pro 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 Pro Preview?
Gemini 3.1 Pro 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 Pro Preview cost?
$2 per million input tokens and $12 per million output tokens, at its provider’s list price.
What is Gemini 3.1 Pro Preview’s context window?
1M tokens (1,048,576).
How does Gemini 3.1 Pro Preview rank?
#19 of 351 on LMArena’s text leaderboard, rated 1480 (95% interval 1477–1483) from 130,819 votes, as of Oct 22, 2026.
Is Gemini 3.1 Pro Preview open source?
No. Gemini 3.1 Pro Preview is proprietary and served through its provider’s API.