Claude Sonnet 5 vs Claude Sonnet 5.5
| Spec | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Respan Index | 48.0 (#48) | 73.4 (#6) |
| Blended price per 1M | $4 | $4 |
| Context window | 1M | 1M |
| Input / output per 1M | $2 / $10 | $2 / $10 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-06-30 | 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 Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Coding | 32.9 Claude Sonnet 5 | 78.8 Claude Sonnet 5.5 |
| Agents | 62.2 Claude Sonnet 5 | 80.1 Claude Sonnet 5.5 |
| Reasoning | 50.6 Claude Sonnet 5 | 79.0 Claude Sonnet 5.5 |
| Knowledge & language | 34.1 Claude Sonnet 5 | 48.6 Claude Sonnet 5.5 |
| Human preference | 54.6 Claude Sonnet 5 | 60.2 Claude Sonnet 5.5 |
Benchmarks both report
Claude Sonnet 5.5 leads on 25 of the 26 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Elo | 1461 | 1473 |
| LMArena Vision (LMArena) | 1261 | 1264 |
| LMArena WebDev (LMArena) | 1539 | 1771 |
| LMArena Agent (LMArena) | 0.01 | 0.1556 |
| MirrorCode (Epoch AI) | 63.3% | 97.8% |
| Chess Puzzles (Epoch AI) | 45% | 59% |
| Terminal-Bench 4.0 (Vals AI) | 10.6% | 64.1% |
| APEX-Agents (Mercor) | 54.5% | 75.5% |
| FrontierMath Tier 4 v2 (Epoch AI) | 29.3% | 80.5% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 65.6% | 88.8% |
| GPQA Diamond | 90.5% | 95.6% |
| LiveBench Agentic Coding (LiveBench) | 59.4% | 56.3% |
| LiveBench Coding (LiveBench) | 80.7% | 91.4% |
| LiveBench Data Analysis (LiveBench) | 71.7% | 78.6% |
| LiveBench Instruction Following (LiveBench) | 63.9% | 70.5% |
| LiveBench Language (LiveBench) | 75% | 83.4% |
| LiveBench Mathematics (LiveBench) | 92.9% | 96.7% |
| LiveBench Reasoning (LiveBench) | 88.7% | 91.6% |
| Mystery Game Puzzles (Epoch AI) | 35% | 65% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.7% | 100% |
| SAGE (Vals AI) | 48.9% | 51.8% |
| SimpleQA Verified | 33.7% | 46.5% |
| Vending-Bench 2 (Andon Labs) | 6377.7 | 11165.28 |
| SimpleBench (SimpleBench) | 60.6% | 75.9% |
| Humanity's Last Exam (no tools) | 43.2% | 56.9% |
| Humanity's Last Exam (with tools) | 57.4% | 64.5% |
FAQ
Is Claude Sonnet 5 better than Claude Sonnet 5.5?
Claude Sonnet 5.5 scores 73.4 on the Respan Index (#6), ahead of Claude Sonnet 5 at 48.0 (#48). Claude Sonnet 5.5 leads on 25 of the 26 benchmarks both report.
Which is cheaper, Claude Sonnet 5 or Claude Sonnet 5.5?
Claude Sonnet 5 lists at $2 input and $10 output per 1M tokens; Claude Sonnet 5.5 at $2 and $10. Both cost about the same per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.
Compare other models
- vsClaude Sonnet 5 vs Claude Sonnet 4.6
- vsClaude Sonnet 5.5 vs Gemini 3.8 Flash
- vsGemini 3.8 Flash vs Claude Sonnet 5
- vsClaude Sonnet 5 vs GPT-5.6 Luna
- vsClaude Sonnet 5 vs Hy4 preview
- vsClaude Sonnet 5 vs GPT-6 Luna
- 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