Claude Opus 5 vs Claude Opus 5.5
Claude Opus 5 is from Anthropic. Claude Opus 5.5 is from Anthropic. Claude Opus 5 costs $25.00 per million output tokens. Claude Opus 5.5 costs $20.00. Claude Opus 5.5 leads on the Epoch Capabilities Index: Claude Opus 5 scores 164.5 and Claude Opus 5.5 scores 168.4. A typical request, about 1,000 words in and 400 words out, costs $0.019 on Claude Opus 5 and $0.015 on Claude Opus 5.5.
Prices updated . Benchmarks updated .
| Claude Opus 5 | Claude Opus 5.5 | |
|---|---|---|
| Lab | Anthropic | Anthropic |
| You send / 1M | $5.00 | $4.00 |
| It replies / 1M | $25.00 | $20.00 |
| Context | 1M | 1M |
| Launched | 2026-07-24 | 2026-09-22 |
| Weights | Closed | Closed |
| Typical request | $0.019 | $0.015 |
| ECI | 164.5 | 168.4 |
| GPQA | 93.9% | 90.6% |
| ARC-AGI-2 | 90.4% | 93.3% |
| HLE | n/a | n/a |
| AIME | 98.9% | 100.0% |
| SimpleQA | 59.9% | 72.2% |
| CritPt | 29.1% | 31.7% |
| Arena | 1,508 | 1,516 |
| Arena web | 1,691 | 1,810 |
Which is cheaper?
Claude Opus 5.5 costs less to run: $20.00 per million output tokens, against $25.00 for Claude Opus 5. Input tokens are $5.00 per million for Claude Opus 5 and $4.00 per million for Claude Opus 5.5. A typical request, about 1,000 words in and 400 words out, costs $0.019 on Claude Opus 5 and $0.015 on Claude Opus 5.5.
Which scores higher?
Claude Opus 5.5 scores higher on Epoch Capabilities Index: 168.4 against 164.5 for Claude Opus 5. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 1M and 1M. Prices are US dollars per million tokens at current public rates.
Verdict
Claude Opus 5.5 is both cheaper and higher on Epoch Capabilities Index than Claude Opus 5, at $20.00 per million output tokens and a score of 168.4. Context is 1M for Claude Opus 5 and 1M for Claude Opus 5.5. Use the model pages for every score on file, including lab-reported numbers.
FAQ
Which is cheaper, Claude Opus 5 vs Claude Opus 5.5?
Claude Opus 5.5 costs less to run: $20.00 per million output tokens, against $25.00 for Claude Opus 5. Input tokens are $5.00 per million for Claude Opus 5 and $4.00 per million for Claude Opus 5.5. A typical request, about 1,000 words in and 400 words out, costs $0.019 on Claude Opus 5 and $0.015 on Claude Opus 5.5.
Which scores higher, Claude Opus 5 vs Claude Opus 5.5?
Claude Opus 5.5 scores higher on Epoch Capabilities Index: 168.4 against 164.5 for Claude Opus 5. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 1M and 1M. Prices are US dollars per million tokens at current public rates.
What is the verdict for Claude Opus 5 vs Claude Opus 5.5?
Claude Opus 5.5 is both cheaper and higher on Epoch Capabilities Index than Claude Opus 5, at $20.00 per million output tokens and a score of 168.4. Context is 1M for Claude Opus 5 and 1M for Claude Opus 5.5. Use the model pages for every score on file, including lab-reported numbers.
Open this pair in the comparison view
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.