Claude Opus 5 vs Claude Sonnet 5.5
| Spec | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| Respan Index | 67.0 (#16) | 73.4 (#6) |
| Blended price per 1M | $10 | $4 |
| Context window | 1M | 1M |
| Input / output per 1M | $5 / $25 | $2 / $10 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-07-24 | 2026-09-28 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| Coding | 64.0 Claude Opus 5 | 78.8 Claude Sonnet 5.5 |
| Agents | 70.4 Claude Opus 5 | 80.1 Claude Sonnet 5.5 |
| Reasoning | 74.0 Claude Opus 5 | 79.0 Claude Sonnet 5.5 |
| Knowledge & language | 61.1 Claude Opus 5 | 48.6 Claude Sonnet 5.5 |
| Human preference | 58.5 Claude Opus 5 | 60.2 Claude Sonnet 5.5 |
Benchmarks both report
Claude Sonnet 5.5 leads on 20 of the 27 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Elo | 1490 | 1473 |
| LMArena Vision (LMArena) | 1285 | 1264 |
| LMArena WebDev (LMArena) | 1692 | 1771 |
| LMArena Agent (LMArena) | 0.0626 | 0.1556 |
| MirrorCode (Epoch AI) | 87.8% | 97.8% |
| Chess Puzzles (Epoch AI) | 43% | 59% |
| APEX-Agents (Mercor) | 65.8% | 75.5% |
| FrontierMath Tier 4 v2 (Epoch AI) | 73.2% | 80.5% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 85.6% | 88.8% |
| FrontierSWE V2 (Proximal Labs) | 52% | 61.9% |
| Furniture Assembly (Epoch AI) | 60.8% | 75% |
| GPQA Diamond | 93.9% | 95.6% |
| LiveBench Agentic Coding (LiveBench) | 65.2% | 56.3% |
| LiveBench Coding (LiveBench) | 81.4% | 91.4% |
| LiveBench Data Analysis (LiveBench) | 74.6% | 78.6% |
| LiveBench Instruction Following (LiveBench) | 63.8% | 70.5% |
| LiveBench Language (LiveBench) | 88.7% | 83.4% |
| LiveBench Mathematics (LiveBench) | 95.7% | 96.7% |
| LiveBench Reasoning (LiveBench) | 91.2% | 91.6% |
| Mystery Game Puzzles (Epoch AI) | 59% | 65% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.9% | 100% |
| SAGE (Vals AI) | 49.4% | 51.8% |
| SimpleQA Verified | 59.9% | 46.5% |
| Terminal-Bench 4.0 (Vals AI) | 53.5% | 64.1% |
| Vending-Bench 2 (Andon Labs) | 11181.87 | 11165.28 |
| Humanity's Last Exam (no tools) | 56.6% | 56.9% |
| SimpleBench (SimpleBench) | 80.6% | 75.9% |
FAQ
Is Claude Opus 5 better than Claude Sonnet 5.5?
Claude Sonnet 5.5 scores 73.4 on the Respan Index (#6), ahead of Claude Opus 5 at 67.0 (#16). Claude Sonnet 5.5 leads on 20 of the 27 benchmarks both report.
Which is cheaper, Claude Opus 5 or Claude Sonnet 5.5?
Claude Opus 5 lists at $5 input and $25 output per 1M tokens; Claude Sonnet 5.5 at $2 and $10. Claude Sonnet 5.5 is 2.5x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.
Compare other models
- vsClaude Opus 5 vs Claude Opus 4.8
- vsClaude Opus 5.5 vs Claude Opus 5
- vsClaude Sonnet 5.5 vs Claude Sonnet 5
- vsClaude Sonnet 5.5 vs Gemini 3.8 Flash
- vsClaude Sonnet 5.5 vs Grok 4.7
- vsClaude Opus 5 vs GPT-6.2 Sol
- vsClaude Opus 5 vs Hy4
- vsClaude Opus 5 vs GPT-6.1 Terra
- vsClaude Sonnet 5.5 vs GPT-6.2 Astra
- vsClaude Sonnet 5.5 vs Claude Fable 5.1
- vsClaude Sonnet 5.5 vs Claude Opus 5.5