Claude Opus 5.5
AnthropicProprietaryReleased Sep 22, 2026
Claude Opus 5.5 ranks #2 on LMArena (1514.8); official output price $20.00 per 1M tokens.
Key metrics
Rank history
LMArena rank, last 14 days#1 on Sep 26, #2 now; best #1 in this period.
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| maxUsed in table | 57.6 | – | 98 | 561 | 561 |
| xhigh | 56.0 | – | 78 | 81 | 81 |
| high | 53.6 | – | 75 | 23 | 23 |
| medium | 51.2 | – | 75 | 15 | 15 |
| low | 42.3 | – | 76 | 5.3 | 5.3 |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 1 |  Gemini 4 Argon | 1533.9 | 52.6 | $10.00 | – |
| 2 | Claude Opus 5.5This page | 1514.8 | 57.6 | $20.00 | 98 |
| 3 | Claude Fable 5.1 | 1510.0 | 53.4 | $50.00 | 72 |
| 4 | Claude Opus 5 | 1507.0 | 50.8 | $25.00 | – |
| 5 | Claude Opus 4.6 | 1502.9 | 31.9 | $25.00 | – |
More from Anthropic
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 3 | Claude Fable 5.1 | 1510.0 | 53.4 | $50.00 | 72 |
| 4 | Claude Opus 5 | 1507.0 | 50.8 | $25.00 | – |
| 5 | Claude Opus 4.6 | 1502.9 | 31.9 | $25.00 | – |
| 8 | Claude Fable 5 | 1491.2 | 49.6 | $50.00 | – |
| 9 | Claude Opus 4.7 | 1489.6 | 40.7 | $25.00 | – |
| 24 | Claude Sonnet 5.5 | 1471.2 | 56.0 | $10.00 | 137 |
Pricing
- Official API list price: $4.00 input and $20.00 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $8.00 per 1M tokens.
- Among 78 models with an output price, it is the #67 cheapest.
- The cheapest OpenRouter route charges $4.00 input / $20.00 output.
Sources & methodology
Claude Opus 5.5 (Anthropic): Arena 1514.8 (#2), Intelligence Index 57.6, $4.00 in / $20.00 out per 1M tokens, 1M context. Data updated Oct 9, 2026.
- LMArena — Arena score, 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
FAQ
What rank is Claude Opus 5.5 right now?
Claude Opus 5.5 is #2 on our leaderboard of 68 scored models (Arena score 1514.8); its raw LMArena rank is #2.
What does Claude Opus 5.5 cost via API?
Input $4.00 / output $20.00 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $8.00 per 1M tokens.
How fast is Claude Opus 5.5?
Artificial Analysis measures about 98 output tokens per second, 561 s to the first token and 561 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is Claude Opus 5.5 to the models ranked next to it?
It is 19.1 points behind Gemini 4 Argon (1533.9) and 4.8 points ahead of Claude Fable 5.1 (1510.0); gaps smaller than the confidence interval (±8.1) are not significant.
Is Claude Opus 5.5 open source? Can it be self-hosted?
Claude Opus 5.5 is a closed model, available only via official APIs or hosted services.
What is the context length of Claude Opus 5.5?
1M (1,000,000 tokens, as listed on OpenRouter).