Gemini 4 Argon
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
Claude Sonnet 4.5
Claude Sonnet 4.5 is a proprietary model from Anthropic, released Sep 29, 2025. It ranks #79 of 351 on the LMArena text leaderboard with a rating of 1438. It costs $3 per million input tokens and $15 per million output tokens, with a 1M-token context window.
- Developer
- Anthropic
- Released
- Sep 29, 2025
- Context window
- 1M
- Price in / out, per 1M tokens
- $3 / $15
- Weights
- Proprietary
- Inputs
- Text, Images, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Oct 1, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 70.00% | 59 / 85 | $0.81 | |
| Vibe Code BenchCoding | 22.62% | 79 / 115 | $6.66 | |
| LiveCodeBenchCoding | 73.00% | 83 / 143 | $3 / $15 | |
| MedCodeMedicine | 40.57% | 63 / 107 | $3 / $15 | |
| MedQAMedicine | 94.71% | 15 / 92 | $3 / $15 | |
| GPQA DiamondReasoning | 81.63% | 63 / 138 | $3 / $15 | |
| MMLU-ProReasoning | 87.36% | 28 / 138 | $3 / $15 | |
| AIMEReasoning | 88.19% | 30 / 96 | $3 / $15 | |
| MMMUReasoning | 79.31% | 48 / 93 | $3 / $15 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1438 | 79 / 351 | 82.7K |
| CodingLMArena | 1488 | 38 / 346 | 19.9K |
| MathLMArena | 1449 | 73 / 339 | 5.1K |
| Creative writingLMArena | 1442 | 41 / 349 | 12.4K |
| Instruction followingLMArena | 1459 | 42 / 351 | 24.4K |
| Hard promptsLMArena | 1462 | 54 / 351 | 48.3K |
| Multi-turnLMArena | 1465 | 43 / 349 | 14.5K |
| Long queriesLMArena | 1475 | 36 / 330 | 26.5K |
| ExpertLMArena | 1482 | 46 / 305 | 6.1K |
| Legal and governmentIndustries | 1450 | 66 / 325 | 6K |
| Medicine and healthcareIndustries | 1444 | 88 / 325 | 5.4K |
| Business and financeIndustries | 1440 | 56 / 344 | 15.8K |
| ChineseLanguages | 1460 | 113 / 328 | 5.9K |
| SpanishLanguages | 1458 | 43 / 249 | 2.5K |
| GermanLanguages | 1427 | 88 / 261 | 1.4K |
| FrenchLanguages | 1458 | 69 / 252 | 2K |
| JapaneseLanguages | 1390 | 89 / 236 | 785 |
| WebDevLMArena | 1394 | 103 / 124 | 13.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Claude Sonnet 4.5 (20250929), Claude Sonnet 4.5 (High, 32K, 20250929)).
Compare Claude Sonnet 4.5
Anthropic
An AI safety and research company that builds the Claude family of models, known for coding, long context and careful behaviour. Founded 2021, based in San Francisco. anthropic.com
Questions
Who makes Claude Sonnet 4.5?
Claude Sonnet 4.5 is made by Anthropic, founded 2021 and based in San Francisco.
How much does Claude Sonnet 4.5 cost?
$3 per million input tokens and $15 per million output tokens, at its provider’s list price.
What is Claude Sonnet 4.5’s context window?
1M tokens (1,000,000).
How does Claude Sonnet 4.5 rank?
#79 of 351 on LMArena’s text leaderboard, rated 1438 (95% interval 1436–1441) from 82,650 votes, as of Oct 22, 2026.
Is Claude Sonnet 4.5 open source?
No. Claude Sonnet 4.5 is proprietary and served through its provider’s API.