Gemini 4 Argon
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 PreviewI
Independent
INTELLECT-3
INTELLECT-3 is an open-weight model. It ranks #203 of 351 on the LMArena text leaderboard with a rating of 1356.
LMArena text1356−1 in 30 days
Rank#203/351
95% interval1348–1364
Votes5.4K
- Developer
- —
- Released
- Dec 11, 2025
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · MIT
- Inputs
- —
- Reasoning
- —
- Tool use
- —
LatestINTELLECT-3 1356
The rating LMArena published at each update since Dec 11, 2025. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1356 | 203 / 351 | 5.4K |
| CodingLMArena | 1375 | 202 / 346 | 1K |
| MathLMArena | 1375 | 189 / 339 | 342 |
| Creative writingLMArena | 1316 | 210 / 349 | 834 |
| Instruction followingLMArena | 1316 | 219 / 351 | 1.5K |
| Hard promptsLMArena | 1352 | 210 / 351 | 2.8K |
| Multi-turnLMArena | 1350 | 203 / 349 | 794 |
| Long queriesLMArena | 1331 | 215 / 330 | 1.4K |
| ExpertLMArena | 1322 | 221 / 305 | 355 |
| Legal and governmentIndustries | 1321 | 236 / 325 | 414 |
| Medicine and healthcareIndustries | 1322 | 233 / 325 | 336 |
| Business and financeIndustries | 1348 | 196 / 344 | 1K |
| ChineseLanguages | 1354 | 216 / 328 | 516 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare INTELLECT-3
Questions
How does INTELLECT-3 rank?
#203 of 351 on LMArena’s text leaderboard, rated 1356 (95% interval 1348–1364) from 5,432 votes, as of Oct 22, 2026.
Is INTELLECT-3 open source?
INTELLECT-3 has open weights under the MIT license.