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 4.5
Grok 4.5 is a proprietary model from xAI, released Jul 8, 2026. It ranks #57 of 351 on the LMArena text leaderboard with a rating of 1448. It costs $2 per million input tokens and $6 per million output tokens, with a 500K-token context window.
- Developer
- xAI
- Released
- Jul 8, 2026
- Context window
- 500K
- Price in / out, per 1M tokens
- $2 / $6
- Weights
- Proprietary
- Inputs
- Text, Images, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Jul 10, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Terminal-Bench 4.0Coding | 8.59% | 42 / 55 | $5.52 | |
| SWE-benchCoding | 86.60% | 13 / 85 | $0.54 | |
| Vibe Code BenchCoding | 69.00% | 45 / 115 | $4.10 | |
| LiveCodeBenchCoding | 87.35% | 15 / 143 | $2 / $6 | |
| Tax Agent BenchFinance | 24.86% | 41 / 76 | $0.47 | |
| Legal Research BenchLaw | 37.98% | 41 / 85 | $1.09 | |
| MedCodeMedicine | 43.29% | 46 / 107 | $2 / $6 | |
| GPQA DiamondReasoning | 92.93% | 13 / 138 | $2 / $6 | |
| MMLU-ProReasoning | 89.22% | 14 / 138 | $2 / $6 | |
| MMMUReasoning | 61.79% | 83 / 93 | $2 / $6 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1448 | 57 / 351 | 39.9K |
| CodingLMArena | 1474 | 61 / 346 | 11.1K |
| MathLMArena | 1460 | 58 / 339 | 1.8K |
| Creative writingLMArena | 1442 | 40 / 349 | 8.3K |
| Instruction followingLMArena | 1445 | 54 / 351 | 14.5K |
| Hard promptsLMArena | 1462 | 53 / 351 | 26.6K |
| Multi-turnLMArena | 1456 | 51 / 349 | 6.6K |
| Long queriesLMArena | 1462 | 47 / 330 | 19.3K |
| ExpertLMArena | 1465 | 65 / 305 | 4.7K |
| Legal and governmentIndustries | 1463 | 47 / 325 | 3.3K |
| Medicine and healthcareIndustries | 1439 | 98 / 325 | 2.9K |
| Business and financeIndustries | 1441 | 54 / 344 | 7.6K |
| ChineseLanguages | 1495 | 59 / 328 | 3.1K |
| SpanishLanguages | 1451 | 60 / 249 | 1.1K |
| GermanLanguages | 1448 | 56 / 261 | 685 |
| FrenchLanguages | 1457 | 72 / 252 | 1.3K |
| JapaneseLanguages | 1431 | 42 / 236 | 540 |
| WebDevLMArena | 1553 | 44 / 124 | 11.1K |
| VisionLMArena | 1287 | 31 / 146 | 12.6K |
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 4.5
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 4.5?
Grok 4.5 is made by xAI, founded 2023 and based in San Francisco Bay Area.
How much does Grok 4.5 cost?
$2 per million input tokens and $6 per million output tokens, at its provider’s list price.
What is Grok 4.5’s context window?
500K tokens (500,000).
How does Grok 4.5 rank?
#57 of 351 on LMArena’s text leaderboard, rated 1448 (95% interval 1444–1452) from 39,880 votes, as of Oct 22, 2026.
Is Grok 4.5 open source?
No. Grok 4.5 is proprietary and served through its provider’s API.