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 Haiku 4.5
Claude Haiku 4.5 is a proprietary model from Anthropic, released Oct 15, 2025. It ranks #161 of 351 on the LMArena text leaderboard with a rating of 1397. It costs $1 per million input tokens and $5 per million output tokens, with a 200K-token context window.
- Developer
- Anthropic
- Released
- Oct 15, 2025
- Context window
- 200K
- Price in / out, per 1M tokens
- $1 / $5
- Weights
- Proprietary
- Inputs
- Text, Images, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Oct 16, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 66.60% | 68 / 85 | $0.37 | |
| Vibe Code BenchCoding | 11.39% | 97 / 115 | $1.31 | |
| LiveCodeBenchCoding | 41.17% | 130 / 143 | $1 / $5 | |
| Tax Agent BenchFinance | 5.86% | 71 / 76 | $0.23 | |
| Legal Research BenchLaw | 10.58% | 75 / 85 | $0.27 | |
| MedCodeMedicine | 32.68% | 88 / 107 | $1 / $5 | |
| MedQAMedicine | 79.57% | 72 / 92 | $1 / $5 | |
| GPQA DiamondReasoning | 72.22% | 90 / 138 | $1 / $5 | |
| MMLU-ProReasoning | 78.72% | 102 / 138 | $1 / $5 | |
| AIMEReasoning | 82.71% | 44 / 96 | $1 / $5 | |
| MMMUReasoning | 46.07% | 91 / 93 | $1 / $5 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1397 | 161 / 351 | 152.4K |
| CodingLMArena | 1454 | 94 / 346 | 39.2K |
| MathLMArena | 1398 | 165 / 339 | 8.5K |
| Creative writingLMArena | 1371 | 143 / 349 | 26.2K |
| Instruction followingLMArena | 1414 | 98 / 351 | 48.9K |
| Hard promptsLMArena | 1420 | 135 / 351 | 94K |
| Multi-turnLMArena | 1409 | 140 / 349 | 26.4K |
| Long queriesLMArena | 1427 | 99 / 330 | 57.9K |
| ExpertLMArena | 1443 | 92 / 305 | 14.1K |
| Legal and governmentIndustries | 1400 | 157 / 325 | 11.5K |
| Medicine and healthcareIndustries | 1394 | 163 / 325 | 10.3K |
| Business and financeIndustries | 1400 | 140 / 344 | 29.3K |
| ChineseLanguages | 1418 | 168 / 328 | 10.8K |
| SpanishLanguages | 1422 | 112 / 249 | 4.5K |
| GermanLanguages | 1374 | 150 / 261 | 2.5K |
| FrenchLanguages | 1410 | 146 / 252 | 4.4K |
| JapaneseLanguages | 1338 | 138 / 236 | 1.8K |
| WebDevLMArena | 1331 | 126 / 124 | 29.1K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Claude Haiku 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 Haiku 4.5?
Claude Haiku 4.5 is made by Anthropic, founded 2021 and based in San Francisco.
How much does Claude Haiku 4.5 cost?
$1 per million input tokens and $5 per million output tokens, at its provider’s list price.
What is Claude Haiku 4.5’s context window?
200K tokens (200,000).
How does Claude Haiku 4.5 rank?
#161 of 351 on LMArena’s text leaderboard, rated 1397 (95% interval 1395–1399) from 152,393 votes, as of Oct 22, 2026.
Is Claude Haiku 4.5 open source?
No. Claude Haiku 4.5 is proprietary and served through its provider’s API.