Claude Opus 5.5 vs Claude Sonnet 5
| Spec | Claude Opus 5.5 | Claude Sonnet 5 |
|---|---|---|
| Respan Index | 76.0 (#4) | 48.0 (#48) |
| Blended price per 1M | $8 | $4 |
| Context window | 1M | 1M |
| Input / output per 1M | $4 / $20 | $2 / $10 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-09-22 | 2026-06-30 |
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 5.5 | Claude Sonnet 5 |
|---|---|---|
| Coding | 75.9 Claude Opus 5.5 | 32.9 Claude Sonnet 5 |
| Agents | 78.7 Claude Opus 5.5 | 62.2 Claude Sonnet 5 |
| Reasoning | 84.1 Claude Opus 5.5 | 50.6 Claude Sonnet 5 |
| Knowledge & language | 70.4 Claude Opus 5.5 | 34.1 Claude Sonnet 5 |
| Human preference | 61.6 Claude Opus 5.5 | 54.6 Claude Sonnet 5 |
Benchmarks both report
Claude Opus 5.5 leads on 24 of the 25 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Opus 5.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Elo | 1506 | 1461 |
| LMArena Vision (LMArena) | 1293 | 1261 |
| LMArena WebDev (LMArena) | 1818 | 1539 |
| LMArena Agent (LMArena) | 0.1863 | 0.01 |
| MirrorCode (Epoch AI) | 95.6% | 63.3% |
| Chess Puzzles (Epoch AI) | 67% | 45% |
| APEX-Agents (Mercor) | 73.5% | 54.5% |
| FrontierMath Tier 4 v2 (Epoch AI) | 95% | 29.3% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 91.2% | 65.6% |
| GPQA Diamond | 90.6% | 90.5% |
| LiveBench Agentic Coding (LiveBench) | 71.7% | 59.4% |
| LiveBench Coding (LiveBench) | 89.3% | 80.7% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 71.7% |
| LiveBench Instruction Following (LiveBench) | 67% | 63.9% |
| LiveBench Language (LiveBench) | 86.3% | 75% |
| LiveBench Mathematics (LiveBench) | 97.1% | 92.9% |
| LiveBench Reasoning (LiveBench) | 92.2% | 88.7% |
| Mystery Game Puzzles (Epoch AI) | 71% | 35% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 94.7% |
| SAGE (Vals AI) | 45.8% | 48.9% |
| SimpleQA Verified | 72.2% | 33.7% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 10.6% |
| Vending-Bench 2 (Andon Labs) | 9235.25 | 6377.7 |
| SimpleBench (SimpleBench) | 88.4% | 60.6% |
| Humanity's Last Exam (with tools) | 67.7% | 57.4% |
FAQ
Is Claude Opus 5.5 better than Claude Sonnet 5?
Claude Opus 5.5 scores 76.0 on the Respan Index (#4), ahead of Claude Sonnet 5 at 48.0 (#48). Claude Opus 5.5 leads on 24 of the 25 benchmarks both report.
Which is cheaper, Claude Opus 5.5 or Claude Sonnet 5?
Claude Opus 5.5 lists at $4 input and $20 output per 1M tokens; Claude Sonnet 5 at $2 and $10. Claude Sonnet 5 is 2.0x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.
Compare other models
- vsClaude Opus 5.5 vs Claude Opus 5
- vsClaude Sonnet 5 vs Claude Sonnet 4.6
- vsClaude Sonnet 5.5 vs Claude Sonnet 5
- vsGemini 3.8 Flash vs Claude Sonnet 5
- vsClaude Opus 5.5 vs Qwen3.8-Max
- vsClaude Opus 5.5 vs Gemini 4 Carbon
- vsClaude Opus 5.5 vs GPT-6.2 Astra
- vsClaude Opus 5.5 vs Gemini 4 Neon
- vsClaude Sonnet 5 vs GPT-5.6 Luna
- vsClaude Sonnet 5 vs Hy4 preview
- vsClaude Sonnet 5 vs GPT-6 Luna