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 Opus 4.8
Claude Opus 4.8 is a proprietary model from Anthropic, released May 27, 2026. It ranks #40 of 351 on the LMArena text leaderboard with a rating of 1461. It costs $5 per million input tokens and $25 per million output tokens, with a 1M-token context window.
- Developer
- Anthropic
- Released
- May 27, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $5 / $25
- Weights
- Proprietary
- Inputs
- Text, Images, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Jun 3, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Terminal-Bench 4.0Coding | 23.23% | 27 / 55 | $17.14 | |
| SWE-benchCoding | 88.60% | 12 / 85 | $1.92 | |
| Vibe Code BenchCoding | 82.72% | 22 / 115 | $26.88 | |
| LiveCodeBenchCoding | 87.82% | 11 / 143 | $5 / $25 | |
| Tax Agent BenchFinance | 30.00% | 30 / 76 | $1.69 | |
| Legal Research BenchLaw | 43.75% | 23 / 85 | $2.82 | |
| MedCodeMedicine | 53.22% | 10 / 107 | $5 / $25 | |
| GPQA DiamondReasoning | 92.42% | 16 / 138 | $5 / $25 | |
| MMLU-ProReasoning | 89.58% | 9 / 138 | $5 / $25 | |
| MMMUReasoning | 86.59% | 19 / 93 | $5 / $25 | |
| Terminal-Bench ScienceReasoning | 4.29% | 29 / 42 | $23.14 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1461 | 40 / 351 | 64.1K |
| CodingLMArena | 1491 | 35 / 346 | 17.4K |
| MathLMArena | 1486 | 27 / 339 | 3K |
| Creative writingLMArena | 1454 | 30 / 349 | 12.8K |
| Instruction followingLMArena | 1477 | 24 / 351 | 22.7K |
| Hard promptsLMArena | 1482 | 36 / 351 | 42.5K |
| Multi-turnLMArena | 1476 | 29 / 349 | 11.2K |
| Long queriesLMArena | 1484 | 20 / 330 | 30.2K |
| ExpertLMArena | 1503 | 26 / 305 | 7.1K |
| Legal and governmentIndustries | 1477 | 34 / 325 | 5.5K |
| Medicine and healthcareIndustries | 1464 | 48 / 325 | 4.8K |
| Business and financeIndustries | 1458 | 37 / 344 | 12.7K |
| ChineseLanguages | 1506 | 46 / 328 | 4.4K |
| SpanishLanguages | 1465 | 35 / 249 | 1.9K |
| GermanLanguages | 1473 | 27 / 261 | 1.1K |
| FrenchLanguages | 1481 | 34 / 252 | 2.2K |
| JapaneseLanguages | 1443 | 37 / 236 | 902 |
| WebDevLMArena | 1556 | 42 / 124 | 18.5K |
| VisionLMArena | 1295 | 23 / 146 | 18.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Claude Opus 4.8 (High), Claude Opus 4.8).
Compare Claude Opus 4.8
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 Opus 4.8?
Claude Opus 4.8 is made by Anthropic, founded 2021 and based in San Francisco.
How much does Claude Opus 4.8 cost?
$5 per million input tokens and $25 per million output tokens, at its provider’s list price.
What is Claude Opus 4.8’s context window?
1M tokens (1,000,000).
How does Claude Opus 4.8 rank?
#40 of 351 on LMArena’s text leaderboard, rated 1461 (95% interval 1457–1465) from 64,096 votes, as of Oct 22, 2026.
Is Claude Opus 4.8 open source?
No. Claude Opus 4.8 is proprietary and served through its provider’s API.