Model comparison
Claude Sonnet 4.6 vs Claude Sonnet 5.5
Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 50.1 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 0 categories and Claude Sonnet 5.5 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 88.7 to 51.9.
- The biggest single-benchmark swing is ProofBench: 45% for Claude Sonnet 4.6 and 100% for Claude Sonnet 5.5.
- Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
Side by side
| Claude Sonnet 4.6 | Claude Sonnet 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 50.1 | 60.5 |
| Released | 2026-02-17 | 2026-09-28 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 128K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $10 |
| Results tracked | 57 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Sonnet 4.6: 46.0 (#62), Claude Sonnet 5.5: 65.5 (#6)
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode | 24.3% | 52.1% |
| LMArena WebDev | 1521 | 1699 |
| SciCode | 46.8% | 61% |
| ALE-Bench | 1,327 | 1,819 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| CursorBench | — | 55.5% |
| FrontierSWE | — | 61.9% |
| WeirdML | 66.1% | — |
| LMArena Coding | 1504 | — |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Sonnet 4.6: 39.1 (#26), Claude Sonnet 5.5: 44.9 (#14)
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agents | 43% | 75.5% |
| Terminal-Bench | 53.4% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 5.5 leads
Claude Sonnet 4.6: 46.1 (#40), Claude Sonnet 5.5: 52.4 (#29)
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| CritPt | 3.1% | 31.4% |
| Mystery Game Puzzles | 16% | 65% |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| LMArena Hard Prompts | 1485 | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| Epoch Capabilities Index | 152.25 | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 5.5 leads
Claude Sonnet 4.6: 51.9 (#41), Claude Sonnet 5.5: 88.7 (#4)
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 100% |
| ProofBench | 45% | 100% |
| FrontierMath (Tiers 1-3) | — | 88.8% |
| FrontierMath Tier 4 | — | 80.5% |
| LMArena Math | 1463 | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 5.5 leads
Claude Sonnet 4.6: 51.6 (#60), Claude Sonnet 5.5: 66.0 (#11)
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | 87.4% | 95.6% |
| SimpleQA Verified | 35.5% | 46.5% |
| Vectara Hallucination Rate | 10.6% | — |
| LMArena Expert | 1500 | — |
Multimodal Claude Sonnet 5.5 leads
Claude Sonnet 4.6: 38.0 (#61), Claude Sonnet 5.5: 53.2 (#5)
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| Furniture Assembly | — | 75% |
| LMArena Document | 1482 | — |
Multilingual Not comparable
Claude Sonnet 4.6: 54.6 (#39), Claude Sonnet 5.5: —
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1491 | — |
| LMArena French | 1465 | — |
| LMArena German | 1428 | — |
| LMArena Japanese | 1419 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1440 | — |
| LMArena Spanish | 1465 | — |
Instruction Following Not comparable
Claude Sonnet 4.6: 77.6 (#23), Claude Sonnet 5.5: —
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Instruction Following | 1476 | — |
Long Context Not comparable
Claude Sonnet 4.6: 45.3 (#40), Claude Sonnet 5.5: —
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Longer Query | 1479 | — |
Writing & Preference Not comparable
Claude Sonnet 4.6: 70.4 (#22), Claude Sonnet 5.5: —
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1435 | — |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
| LMArena Multi-Turn | 1464 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Claude Sonnet 5.5?
Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 50.1 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.6 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 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Claude Sonnet 5.5 better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 65.5 versus 46.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.6 and Claude Sonnet 5.5 share?
11 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Claude Sonnet 5.5 has 16.