Model comparison
Claude Sonnet 5 vs Claude Sonnet 5.5
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 54.6 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Sonnet 5 scores higher in 1 category and Claude Sonnet 5.5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 66.2.
- The biggest single-benchmark swing is FrontierMath Tier 4: 29.3% for Claude Sonnet 5 and 80.5% for Claude Sonnet 5.5.
- Both cost about the same: $2 input and $10 output per million tokens.
Side by side
| Claude Sonnet 5 | Claude Sonnet 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 54.6 | 61.9 |
| Released | 2026-06-29 | 2026-09-28 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 51 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Sonnet 5: 55.5 (#26), Claude Sonnet 5.5: 67.3 (#6)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode | 42.7% | 52.1% |
| CursorBench | 34.1% | 55.5% |
| LMArena WebDev | 1541 | 1774 |
| SciCode | 54.3% | 61% |
| LMArena Coding | 1483 | 1513 |
| ALE-Bench | 1,463 | 1,819 |
| DeepSWE | 53.8% | — |
| FrontierSWE | — | 61.9% |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Sonnet 5: 42.8 (#18), Claude Sonnet 5.5: 45.0 (#16)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agents | 54.5% | 75.5% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5.5 leads
Claude Sonnet 5: 49.1 (#39), Claude Sonnet 5.5: 54.0 (#28)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| NYT Connections (extended) | 75.1% | 80.5% |
| CritPt | 16.9% | 31.4% |
| LMArena Hard Prompts | 1461 | 1495 |
| Mystery Game Puzzles | 35% | 65% |
| Epoch Capabilities Index | 156.21 | 165.03 |
| SimpleBench | 60.6% | — |
| Chess Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5.5 leads
Claude Sonnet 5: 66.2 (#27), Claude Sonnet 5.5: 87.9 (#6)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 88.8% |
| FrontierMath Tier 4 | 29.3% | 80.5% |
| OTIS Mock AIME 2024-2025 | 94.7% | 100% |
| ProofBench | 77% | 100% |
| LMArena Math | 1467 | 1510 |
| FrontierMath Erdős | — | 2.9% |
Knowledge Claude Sonnet 5.5 leads
Claude Sonnet 5: 55.6 (#47), Claude Sonnet 5.5: 66.0 (#12)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | 90.5% | 95.6% |
| SimpleQA Verified | 33.7% | 46.5% |
| LMArena Expert | 1490 | 1540 |
Multimodal Claude Sonnet 5.5 leads
Claude Sonnet 5: 42.4 (#31), Claude Sonnet 5.5: 51.5 (#6)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Vision | 1274 | 1289 |
| Blueprint-Bench 2 | 24.9% | — |
| Furniture Assembly | — | 75% |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5.5 leads
Claude Sonnet 5: 53.8 (#55), Claude Sonnet 5.5: 55.3 (#30)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Non-English | 1431 | 1452 |
| LMArena Chinese | 1477 | 1522 |
| LMArena Russian | 1451 | 1451 |
| LMArena French | 1460 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Spanish | 1437 | — |
Instruction Following Claude Sonnet 5.5 leads
Claude Sonnet 5: 76.3 (#41), Claude Sonnet 5.5: 78.3 (#11)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1495 |
Long Context Claude Sonnet 5.5 leads
Claude Sonnet 5: 44.8 (#55), Claude Sonnet 5.5: 45.9 (#28)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Longer Query | 1463 | 1498 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Claude Sonnet 5.5: 66.0 (#40)
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Text | 1442 | 1471 |
| LMArena Creative Writing | 1416 | 1465 |
| LMArena Multi-Turn | 1454 | 1474 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Claude Sonnet 5.5?
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 54.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 5 or Claude Sonnet 5.5?
Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Claude Sonnet 5.5 better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 5 and Claude Sonnet 5.5 share?
29 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Claude Sonnet 5.5 has 32.