Claude Sonnet 4.6 vs Claude Sonnet 5.5
Updated October 21, 2026. 75 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
vs boards won of 75 shared
Decision reading
Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6.
Pick Claude Sonnet 4.6 when what matters is LiveBench data analysis or LMArena Text: Spanish, where it leads.
Model AClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved taskModel BClaude Sonnet 5.5Anthropic88.9/1002 independent benchmarksNo cost per solved task
- Shared results
- 75
- Claude Sonnet 4.6 only
- 42
- Claude Sonnet 5.5 only
- 20
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Claude Sonnet 5.5
Claude Sonnet 5.5 scores 88.9 against 57.8.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Sonnet 5.5
Claude Sonnet 5.5 leads, 56.0 against 30.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Sonnet 4.6 has a AA Agentic Index result, 31.8.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Sonnet 4.6 has a GPQA Diamond result, 85.6%.
Directional only
Math
AIME
No call
Only Claude Sonnet 4.6 has a AIME result, 92.3%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Sonnet 4.6 has a MMLU Pro result, 87.3%.
Directional only
Web design
Design Arena: websites
Claude Sonnet 5.5
Claude Sonnet 5.5 leads, 1326 against 1285.
Same board, both measured
General
Vals Index
No call
Only Claude Sonnet 5.5 has a Vals Index result, 70.8%.
Directional only
Long documents
Listed context window
No call
Both take 1M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Sonnet 5.5
Claude Sonnet 4.6 $0.011, Claude Sonnet 5.5 $0.0070 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Sonnet 4.6 has the number, $1.68.
Directional only
At a glance
- Coding index
- Claude Sonnet 4.6 57.8 from 2 benchmarks, Claude Sonnet 5.5 88.9 from 2 benchmarks.
- Widest category
- Intelligence, 21.3 points apart on average over 2 shared benchmarks.
- Widest single gap
- LiveBench long agentic: Claude Sonnet 4.6 23.1% against Claude Sonnet 5.5 78.8%, 55.7 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.6 $15.00 against Claude Sonnet 5.5 $10.00 per million output tokens, 1.5x apart.
- Context window
- Both take 1M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Sonnet 4.6 | Bars | Claude Sonnet 5.5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 13 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 11 | ||
| Reasoning | 0 | 10 | ||
| Math | 0 | 4 | ||
| Knowledge | 0 | 5 | ||
| Web design | 0 | 7 | ||
| General | 4 | 19 | ||
| All shared boards | 4 | 71 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index013
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| LiveBench coding | 66.6% | 94.7% | Claude Sonnet 5.5 |
| LMArena WebDev | 1523 | 1768 | Claude Sonnet 5.5 |
| AA Coding Index | 63.0 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveCodeBench (Vals AI) | 82.1% | Not measured | Only Claude Sonnet 4.6 measured |
| SWE-bench Verified (Vals AI) | 77.4% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 64.1% | Only Claude Sonnet 5.5 measured |
| Vibe Code Bench (Vals AI) | 55.8% | 92.4% | Claude Sonnet 5.5 |
| Code migration (Vals AI) | 39.9% | 69.8% | Claude Sonnet 5.5 |
| ProgramBench (Vals AI) | 0.5% | 6.5% | Claude Sonnet 5.5 |
| IOI (Vals AI) | Not measured | 83.1% | Only Claude Sonnet 5.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 57.3% | 83.2% | Claude Sonnet 5.5 |
| SWE-bench Multimodal (Vals AI) | Not measured | 58.3% | Only Claude Sonnet 5.5 measured |
| SkillsBench (Vals AI) | 49.0% | Not measured | Only Claude Sonnet 4.6 measured |
| CyberBench (Vals AI) | Not measured | 59.6% | Only Claude Sonnet 5.5 measured |
| SciCode | 50.1% | 61.0% | Claude Sonnet 5.5 |
| Terminal-Bench Hard (Artificial Analysis run) | 53.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench | 53.4% | Not measured | Only Claude Sonnet 4.6 measured |
| FrontierCode | 24.3% | 52.1% | Claude Sonnet 5.5 |
| FrontierSWE | Not measured | 61.9% | Only Claude Sonnet 5.5 measured |
| WeirdML | 66.1% | Not measured | Only Claude Sonnet 4.6 measured |
| ALE-Bench | Not measured | 1819.1 | Only Claude Sonnet 5.5 measured |
| LMArena Text: coding | 1503 | 1513 | Claude Sonnet 5.5 |
| LMArena Text: software and IT | 1491 | 1504 | Claude Sonnet 5.5 |
| LMArena WebDev: React | 1512 | 1817 | Claude Sonnet 5.5 |
| LMArena WebDev: HTML | 1527 | 1741 | Claude Sonnet 5.5 |
| LMArena WebDev: from an image | 1529 | 1737 | Claude Sonnet 5.5 |
| Neither model has a result on the other 12 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.1 | 56.0 | Claude Sonnet 5.5 |
| Epoch Capabilities Index | 152.8 | 166.2 | Claude Sonnet 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 31.8 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building web apps | 1190 | 1303 | Claude Sonnet 5.5 |
| Design Arena: agents building full-stack apps | 1213 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building mobile apps | 1212 | 1265 | Claude Sonnet 5.5 |
| Design Arena: agents building Android apps | 1202 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building Godot games | 1226 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building games | 1177 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: spreadsheets | Not measured | 1245 | Only Claude Sonnet 5.5 measured |
| LiveBench research | 63.6% | 83.6% | Claude Sonnet 5.5 |
| LiveBench browser | 68.0% | 84.0% | Claude Sonnet 5.5 |
| LiveBench long agentic | 23.1% | 78.8% | Claude Sonnet 5.5 |
| SREBench (Vals AI) | Not measured | 30.1% | Only Claude Sonnet 5.5 measured |
| Finance Agent (Vals AI) | 51.0% | 58.1% | Claude Sonnet 5.5 |
| Tax Agent Bench (Vals AI) | 25.8% | 42.0% | Claude Sonnet 5.5 |
| Legal Research Bench (Vals AI) | 38.5% | 48.1% | Claude Sonnet 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 10.4% | Only Claude Sonnet 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 60.2% | 75.7% | Claude Sonnet 5.5 |
| BioMysteryBench (Vals AI) | Not measured | 81.1% | Only Claude Sonnet 5.5 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 47.1% | Only Claude Sonnet 5.5 measured |
| Vals Science Index | Not measured | 59.1% | Only Claude Sonnet 5.5 measured |
| τ²-Bench Telecom | 79.5% | Not measured | Only Claude Sonnet 4.6 measured |
| APEX-Agents | 43.0% | 75.5% | Claude Sonnet 5.5 |
| OSWorld 2.0 | 9.3% | Not measured | Only Claude Sonnet 4.6 measured |
| DeepResearch Bench | 54.9% | Not measured | Only Claude Sonnet 4.6 measured |
| OSWorld | 72.1% | Not measured | Only Claude Sonnet 4.6 measured |
| SpireClimb | Not measured | 1.3% | Only Claude Sonnet 5.5 measured |
| Vending-Bench 2 | $7,204 | $11,165 | Claude Sonnet 5.5 |
| Neither model has a result on the other 12 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench reasoning | 86.4% | 91.6% | Claude Sonnet 5.5 |
| MysteryMechanism (Vals AI) | Not measured | 49.1% | Only Claude Sonnet 5.5 measured |
| MMMU Pro (Vals AI) | 83.6% | Not measured | Only Claude Sonnet 4.6 measured |
| GPQA Diamond (Artificial Analysis run) | 87.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Humanity's Last Exam (Artificial Analysis run) | 33.6% | 55.0% | Claude Sonnet 5.5 |
| GPQA Diamond (Epoch AI run) | 87.4% | 95.6% | Claude Sonnet 5.5 |
| ARC-AGI | 86.5% | Not measured | Only Claude Sonnet 4.6 measured |
| ARC-AGI-2 | 60.4% | Not measured | Only Claude Sonnet 4.6 measured |
| Chess puzzles | 23.0% | 59.0% | Claude Sonnet 5.5 |
| Mystery game puzzles | 16.0% | 65.0% | Claude Sonnet 5.5 |
| LMArena Text: hard prompts | 1485 | 1494 | Claude Sonnet 5.5 |
| LMArena Text: expert | 1500 | 1531 | Claude Sonnet 5.5 |
| LMArena Text: hard prompts in English | 1493 | 1502 | Claude Sonnet 5.5 |
| LMArena Vision: diagrams | 1306 | 1329 | Claude Sonnet 5.5 |
| LMArena Vision: homework | 1311 | 1331 | Claude Sonnet 5.5 |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| AIME | 92.3% | Not measured | Only Claude Sonnet 4.6 measured |
| OTIS Mock AIME | 85.8% | 100.0% | Claude Sonnet 5.5 |
| FrontierMath, tiers 1 to 3 | Not measured | 88.8% | Only Claude Sonnet 5.5 measured |
| FrontierMath, tier 4 | Not measured | 80.5% | Only Claude Sonnet 5.5 measured |
| ProofBench | 45.0% | 100.0% | Claude Sonnet 5.5 |
| LMArena Text: math | 1462 | 1497 | Claude Sonnet 5.5 |
| LMArena Text: mathematical work | 1483 | 1510 | Claude Sonnet 5.5 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | Not measured | Only Claude Sonnet 4.6 measured |
| LegalBench (Vals AI) | 82.1% | Not measured | Only Claude Sonnet 4.6 measured |
| CaseLaw (Vals AI) | 64.0% | Not measured | Only Claude Sonnet 4.6 measured |
| CorpFin (Vals AI) | 65.3% | Not measured | Only Claude Sonnet 4.6 measured |
| TaxEval (Vals AI) | 77.1% | Not measured | Only Claude Sonnet 4.6 measured |
| MortgageTax (Vals AI) | 67.7% | Not measured | Only Claude Sonnet 4.6 measured |
| MedQA (Vals AI) | 92.1% | Not measured | Only Claude Sonnet 4.6 measured |
| MedCode (Vals AI) | Not measured | 52.9% | Only Claude Sonnet 5.5 measured |
| SimpleQA Verified | 35.5% | 46.5% | Claude Sonnet 5.5 |
| LMArena Text: science | 1474 | 1483 | Claude Sonnet 5.5 |
| LMArena Text: medicine and healthcare | 1451 | 1464 | Claude Sonnet 5.5 |
| LMArena Text: legal and government | 1470 | 1483 | Claude Sonnet 5.5 |
| LMArena Text: business and finance | 1464 | 1468 | Claude Sonnet 5.5 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1285 | 1326 | Claude Sonnet 5.5 |
| Design Arena: UI components | 1271 | 1367 | Claude Sonnet 5.5 |
| Design Arena: game dev | 1259 | 1469 | Claude Sonnet 5.5 |
| Design Arena: data viz | 1278 | 1389 | Claude Sonnet 5.5 |
| Design Arena: 3D | 1234 | 1458 | Claude Sonnet 5.5 |
| Design Arena: all code categories | 1276 | 1364 | Claude Sonnet 5.5 |
| Design Arena: SVG | 1196 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: ASCII art | 1235 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench design | 71.8% | 85.0% | Claude Sonnet 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index419
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 70.8% | Only Claude Sonnet 5.5 measured |
| LiveBench data analysis | 76.1% | 59.5% | Claude Sonnet 4.6 |
| Public Benefits Bench (Vals AI) | 62.5% | 67.2% | Claude Sonnet 5.5 |
| SAGE (Vals AI) | 46.6% | 51.8% | Claude Sonnet 5.5 |
| MedScribe (Vals AI) | Not measured | 91.1% | Only Claude Sonnet 5.5 measured |
| Vals Multimodal Index | 60.6% | Not measured | Only Claude Sonnet 4.6 measured |
| IFBench | 56.6% | Not measured | Only Claude Sonnet 4.6 measured |
| Long context reasoning (AA-LCR) | 80.0% | 82.7% | Claude Sonnet 5.5 |
| DTBench | 89.9% | 97.3% | Claude Sonnet 5.5 |
| LMCA | 46.5% | 68.3% | Claude Sonnet 5.5 |
| Furniture assembly | Not measured | 75.0% | Only Claude Sonnet 5.5 measured |
| ExploitBench | 23.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text | 1458 | 1473 | Claude Sonnet 5.5 |
| LMArena Text: instruction following | 1476 | 1492 | Claude Sonnet 5.5 |
| LMArena Text: creative writing | 1435 | 1467 | Claude Sonnet 5.5 |
| LMArena Vision | 1283 | 1287 | Claude Sonnet 5.5 |
| LMArena Text: English | 1472 | 1484 | Claude Sonnet 5.5 |
| LMArena Text: non-English | 1440 | 1456 | Claude Sonnet 5.5 |
| LMArena Text: Chinese | 1491 | 1535 | Claude Sonnet 5.5 |
| LMArena Text: German | 1428 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: Japanese | 1420 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: Korean | 1410 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: French | 1465 | 1499 | Claude Sonnet 5.5 |
| LMArena Text: Spanish | 1464 | 1451 | Claude Sonnet 4.6 |
| LMArena Text: Russian | 1440 | 1454 | Claude Sonnet 5.5 |
| LMArena Text: Polish | 1443 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: multi-turn | 1464 | 1465 | Claude Sonnet 5.5 |
| LMArena Text: longer queries | 1479 | 1495 | Claude Sonnet 5.5 |
| LMArena Text: writing and language | 1444 | 1474 | Claude Sonnet 5.5 |
| LMArena Text: entertainment and media | 1431 | 1461 | Claude Sonnet 5.5 |
| LMArena Vision: English | 1298 | 1289 | Claude Sonnet 4.6 |
| LMArena Vision: Chinese | 1307 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: reading text | 1296 | 1297 | Claude Sonnet 5.5 |
| LMArena Vision: humor | 1248 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: recognizing things | 1195 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: creative writing | 1272 | 1242 | Claude Sonnet 4.6 |
| LMArena Document | 1482 | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 9 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5.5 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Claude Sonnet 4.6$0.011Fits in one request
Claude Sonnet 5.5$0.0070Fits in one request
Claude Sonnet 5.5 costs less
Repository review
50K input + 3K output tokens
Claude Sonnet 4.6$0.195Fits in one request
Claude Sonnet 5.5$0.130Fits in one request
Claude Sonnet 5.5 costs less
Agent loop
200K input + 10K output tokens
Claude Sonnet 4.6$0.750Fits in one request
Claude Sonnet 5.5$0.500Fits in one request
Claude Sonnet 5.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Sonnet 4.6 | Anthropic Claude Sonnet 5.5 |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Weights | No public weights listed | No public weights listed |
| Released | February 17, 2026 | September 28, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $3.00 | $2.00 |
| Output $/Mtok | $15.00 | $10.00 |
| Coding index | 57.8 | 88.9 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $1.68 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.6 better than Claude Sonnet 5.5 for coding?
Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 when what matters is LiveBench data analysis or LMArena Text: Spanish, where it leads.
Which is cheaper, Claude Sonnet 4.6 or Claude Sonnet 5.5?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Sonnet 5.5 costs $2.00 and $10.00. Cost per solved task is known for Claude Sonnet 4.6 only.
Which has the bigger context window, Claude Sonnet 4.6 or Claude Sonnet 5.5?
Neither: both take 1M tokens.
How many benchmarks is the Claude Sonnet 4.6 vs Claude Sonnet 5.5 comparison based on?
75 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.6's coding index rests on 2 independent benchmarks and Claude Sonnet 5.5's on 2. Where only one model has a result, the page says so instead of naming a winner.