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
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
Grok 4
Grok 4 is a proprietary model from xAI. It ranks #139 of 351 on the LMArena text leaderboard with a rating of 1411.
- Developer
- xAI
- Released
- Jul 15, 2025
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Proprietary
- Inputs
- —
- Reasoning
- —
- Tool use
- —
The rating LMArena published at each update since Jul 15, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 57.80% | 76 / 85 | $1.42 | |
| LiveCodeBenchCoding | 83.25% | 50 / 143 | $3 / $15 | |
| MedCodeMedicine | 38.08% | 73 / 107 | $3 / $15 | |
| MedQAMedicine | 92.49% | 31 / 92 | $3 / $15 | |
| GPQA DiamondReasoning | 88.13% | 35 / 138 | $3 / $15 | |
| MMLU-ProReasoning | 85.30% | 59 / 138 | $3 / $15 | |
| AIMEReasoning | 90.56% | 27 / 96 | $3 / $15 | |
| MMMUReasoning | 76.27% | 54 / 93 | $3 / $15 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1411 | 139 / 351 | 39.7K |
| CodingLMArena | 1408 | 166 / 346 | 8K |
| MathLMArena | 1422 | 116 / 339 | 2.3K |
| Creative writingLMArena | 1397 | 106 / 349 | 5.3K |
| Instruction followingLMArena | 1387 | 148 / 351 | 10.8K |
| Hard promptsLMArena | 1409 | 153 / 351 | 19.4K |
| Multi-turnLMArena | 1416 | 123 / 349 | 6.2K |
| Long queriesLMArena | 1408 | 134 / 330 | 8.9K |
| ExpertLMArena | 1415 | 142 / 305 | 2.1K |
| Legal and governmentIndustries | 1428 | 115 / 325 | 2.6K |
| Medicine and healthcareIndustries | 1435 | 105 / 325 | 2.2K |
| Business and financeIndustries | 1388 | 160 / 344 | 7.1K |
| ChineseLanguages | 1427 | 156 / 328 | 2.8K |
| SpanishLanguages | 1420 | 116 / 249 | 1K |
| GermanLanguages | 1429 | 86 / 261 | 905 |
| FrenchLanguages | 1418 | 137 / 252 | 591 |
| JapaneseLanguages | 1394 | 85 / 236 | 923 |
| VisionLMArena | 1210 | 89 / 146 | 30.2K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Grok 4
xAI
The lab behind Grok, trained on one of the largest compute clusters and integrated with X. Founded 2023, based in San Francisco Bay Area. x.ai
Questions
Who makes Grok 4?
Grok 4 is made by xAI, founded 2023 and based in San Francisco Bay Area.
How does Grok 4 rank?
#139 of 351 on LMArena’s text leaderboard, rated 1411 (95% interval 1407–1415) from 39,679 votes, as of Oct 22, 2026.
Is Grok 4 open source?
No. Grok 4 is proprietary and served through its provider’s API.