Claude Sonnet 5.5 vs GPT-5.3-Codex
Claude Sonnet 5.5 leads GPT-5.3-Codex on coding, 87.3 to 60.0 on the Vibe Coding Index, and Claude Sonnet 5.5 costs 1.4x less per output token ($10.00 vs $14.00 per million). Updated October 21, 2026; 20 benchmarks have a result for both.
vs boards won of 20 shared
Claude Sonnet 5.5 or GPT-5.3-Codex: which to pick
Pick Claude Sonnet 5.5 for coding: it scores 87.3 on the Vibe Coding Index against 60.0 for GPT-5.3-Codex.
Pick GPT-5.3-Codex for work measured by Long context reasoning (AA-LCR), where it leads.
Model AClaude Sonnet 5.5Anthropic87.3/1005 independent benchmarksNo cost per solved taskModel BGPT-5.3-CodexOpenAI60.0/1003 independent benchmarks$0.59 per solved task
- Shared results
- 20
- Claude Sonnet 5.5 only
- 76
- GPT-5.3-Codex only
- 14
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
Claude Sonnet 5.5
Claude Sonnet 5.5 scores 87.3 against 60.0.
5 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Sonnet 5.5
Claude Sonnet 5.5 leads, 56.0 against 32.5.
Same board, both measured
Web design
Design Arena: websites
Claude Sonnet 5.5
Claude Sonnet 5.5 leads, 1326 against 1163.
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
Claude Sonnet 5.5
Claude Sonnet 5.5 takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Sonnet 5.5
Claude Sonnet 5.5 $0.0070, GPT-5.3-Codex $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.3-Codex has the number, $0.59.
Directional only
At a glance
- Coding index
- Claude Sonnet 5.5 87.3 from 5 benchmarks, GPT-5.3-Codex 60.0 from 3 benchmarks.
- Widest category
- Web design, 33.2 points apart on average over 6 shared benchmarks.
- Widest single gap
- Design Arena: 3D: Claude Sonnet 5.5 1452 against GPT-5.3-Codex 1008, 55.5 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 5.5 $10.00 against GPT-5.3-Codex $14.00 per million output tokens, 1.4x apart.
- Context window
- Claude Sonnet 5.5 takes 1M tokens, GPT-5.3-Codex 400K.
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 5.5 | Bars | GPT-5.3-Codex | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 1 | 0 | ||
| Web design | 6 | 0 | ||
| General | 0 | 1 | ||
| All shared boards | 19 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| LiveBench coding | 94.7% | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena WebDev | 1768 | 1407 | Claude Sonnet 5.5 |
| LiveCodeBench (Vals AI) | Not measured | 87.3% | Only GPT-5.3-Codex measured |
| SWE-bench Verified (Vals AI) | Not measured | 78.0% | Only GPT-5.3-Codex measured |
| Terminal-Bench 4 (Vals AI) | 64.1% | Not measured | Only Claude Sonnet 5.5 measured |
| Vibe Code Bench (Vals AI) | 92.4% | 61.8% | Claude Sonnet 5.5 |
| Code migration (Vals AI) | 69.8% | Not measured | Only Claude Sonnet 5.5 measured |
| ProgramBench (Vals AI) | 6.5% | Not measured | Only Claude Sonnet 5.5 measured |
| IOI (Vals AI) | 83.1% | 53.8% | Claude Sonnet 5.5 |
| Terminal-Bench 2.1 (Vals AI) | 83.2% | Not measured | Only Claude Sonnet 5.5 measured |
| SWE-bench Multimodal (Vals AI) | 58.3% | Not measured | Only Claude Sonnet 5.5 measured |
| CyberBench (Vals AI) | 59.6% | Not measured | Only Claude Sonnet 5.5 measured |
| SciCode | 61.0% | Not measured | Only Claude Sonnet 5.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 53.0% | Only GPT-5.3-Codex measured |
| Terminal-Bench | Not measured | 78.4% | Only GPT-5.3-Codex measured |
| FrontierCode | 52.1% | Not measured | Only Claude Sonnet 5.5 measured |
| FrontierSWE | 61.9% | Not measured | Only Claude Sonnet 5.5 measured |
| WeirdML | Not measured | 79.3% | Only GPT-5.3-Codex measured |
| ALE-Bench | 1819.1 | 1655.2 | Claude Sonnet 5.5 |
| LMArena Text: coding | 1513 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: software and IT | 1504 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena WebDev: React | 1817 | 1395 | Claude Sonnet 5.5 |
| LMArena WebDev: HTML | 1741 | 1422 | Claude Sonnet 5.5 |
| LMArena WebDev: from an image | 1737 | 1443 | Claude Sonnet 5.5 |
| SciCode | 13.8% | Not measured | Only Claude Sonnet 5.5 measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 56.0 | 32.5 | Claude Sonnet 5.5 |
| Epoch Capabilities Index | 166.2 | 157.1 | Claude Sonnet 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1306 | 1032 | Claude Sonnet 5.5 |
| Design Arena: agents building full-stack apps | Not measured | 983 | Only GPT-5.3-Codex measured |
| Design Arena: agents building mobile apps | 1257 | 1054 | Claude Sonnet 5.5 |
| Design Arena: agents building Android apps | Not measured | 1084 | Only GPT-5.3-Codex measured |
| Design Arena: agents building Godot games | Not measured | 1124 | Only GPT-5.3-Codex measured |
| Design Arena: spreadsheets | 1244 | Not measured | Only Claude Sonnet 5.5 measured |
| LiveBench research | 83.6% | Not measured | Only Claude Sonnet 5.5 measured |
| LiveBench browser | 84.0% | Not measured | Only Claude Sonnet 5.5 measured |
| LiveBench long agentic | 78.8% | Not measured | Only Claude Sonnet 5.5 measured |
| SREBench (Vals AI) | 30.1% | Not measured | Only Claude Sonnet 5.5 measured |
| Finance Agent (Vals AI) | 58.1% | Not measured | Only Claude Sonnet 5.5 measured |
| Tax Agent Bench (Vals AI) | 42.0% | Not measured | Only Claude Sonnet 5.5 measured |
| Legal Research Bench (Vals AI) | 48.1% | Not measured | Only Claude Sonnet 5.5 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.4% | Not measured | Only Claude Sonnet 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 75.7% | Not measured | Only Claude Sonnet 5.5 measured |
| BioMysteryBench (Vals AI) | 81.1% | Not measured | Only Claude Sonnet 5.5 measured |
| Terminal-Bench-Science (Vals AI) | 47.1% | Not measured | Only Claude Sonnet 5.5 measured |
| Vals Science Index | 59.1% | Not measured | Only Claude Sonnet 5.5 measured |
| τ²-Bench Telecom | Not measured | 86.0% | Only GPT-5.3-Codex measured |
| APEX-Agents | 75.5% | Not measured | Only Claude Sonnet 5.5 measured |
| METR time horizons | Not measured | 74.5% | Only GPT-5.3-Codex measured |
| SpireClimb | 1.3% | Not measured | Only Claude Sonnet 5.5 measured |
| Vending-Bench 2 | $11,165 | $5,940 | Claude Sonnet 5.5 |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| LiveBench reasoning | 91.6% | Not measured | Only Claude Sonnet 5.5 measured |
| MysteryMechanism (Vals AI) | 49.1% | Not measured | Only Claude Sonnet 5.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 91.5% | Only GPT-5.3-Codex measured |
| Humanity's Last Exam (Artificial Analysis run) | 55.0% | 42.5% | Claude Sonnet 5.5 |
| GPQA Diamond (Epoch AI run) | 95.6% | Not measured | Only Claude Sonnet 5.5 measured |
| Chess puzzles | 59.0% | Not measured | Only Claude Sonnet 5.5 measured |
| Mystery game puzzles | 65.0% | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: hard prompts | 1494 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: expert | 1531 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: hard prompts in English | 1502 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Vision: diagrams | 1329 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Vision: homework | 1331 | Not measured | Only Claude Sonnet 5.5 measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Claude Sonnet 5.5 measured |
| FrontierMath, tiers 1 to 3 | 88.8% | Not measured | Only Claude Sonnet 5.5 measured |
| FrontierMath, tier 4 | 80.5% | Not measured | Only Claude Sonnet 5.5 measured |
| ProofBench | 100.0% | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: math | 1497 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: mathematical work | 1510 | Not measured | Only Claude Sonnet 5.5 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 52.9% | Not measured | Only Claude Sonnet 5.5 measured |
| SimpleQA Verified | 46.5% | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: science | 1483 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: medicine and healthcare | 1464 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: legal and government | 1483 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: business and finance | 1468 | Not measured | Only Claude Sonnet 5.5 measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Design Arena: websites | 1326 | 1163 | Claude Sonnet 5.5 |
| Design Arena: UI components | 1365 | 1137 | Claude Sonnet 5.5 |
| Design Arena: game dev | 1469 | 1161 | Claude Sonnet 5.5 |
| Design Arena: data viz | 1394 | 1164 | Claude Sonnet 5.5 |
| Design Arena: 3D | 1452 | 1008 | Claude Sonnet 5.5 |
| Design Arena: all code categories | 1364 | 1145 | Claude Sonnet 5.5 |
| Design Arena: SVG | Not measured | 1129 | Only GPT-5.3-Codex measured |
| Design Arena: ASCII art | Not measured | 1152 | Only GPT-5.3-Codex measured |
| LiveBench design | 85.0% | Not measured | Only Claude Sonnet 5.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Vals Index | 70.8% | Not measured | Only Claude Sonnet 5.5 measured |
| LiveBench data analysis | 59.5% | Not measured | Only Claude Sonnet 5.5 measured |
| Public Benefits Bench (Vals AI) | 67.2% | Not measured | Only Claude Sonnet 5.5 measured |
| SAGE (Vals AI) | 51.8% | Not measured | Only Claude Sonnet 5.5 measured |
| MedScribe (Vals AI) | 91.1% | Not measured | Only Claude Sonnet 5.5 measured |
| IFBench | Not measured | 75.4% | Only GPT-5.3-Codex measured |
| Long context reasoning (AA-LCR) | 82.7% | 83.3% | GPT-5.3-Codex |
| DTBench | 97.3% | Not measured | Only Claude Sonnet 5.5 measured |
| LMCA | 68.3% | Not measured | Only Claude Sonnet 5.5 measured |
| Furniture assembly | 75.0% | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text | 1473 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: instruction following | 1492 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: creative writing | 1467 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Vision | 1287 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: English | 1484 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: non-English | 1456 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: Chinese | 1535 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: French | 1499 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: Spanish | 1451 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: Russian | 1454 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: multi-turn | 1465 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: longer queries | 1495 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: writing and language | 1474 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Text: entertainment and media | 1461 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Vision: English | 1289 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Vision: reading text | 1297 | Not measured | Only Claude Sonnet 5.5 measured |
| LMArena Vision: creative writing | 1242 | Not measured | Only Claude Sonnet 5.5 measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 5.5 | GPT-5.3-Codex | 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 5.5$0.0070Fits in one request
GPT-5.3-Codex$0.0088Fits in one request
Claude Sonnet 5.5 costs less
Repository review
50K input + 3K output tokens
Claude Sonnet 5.5$0.130Fits in one request
GPT-5.3-Codex$0.130Fits in one request
GPT-5.3-Codex costs less
Agent loop
200K input + 10K output tokens
Claude Sonnet 5.5$0.500Fits in one request
GPT-5.3-Codex$0.490Fits in one request
GPT-5.3-Codex 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 5.5 | OpenAI GPT-5.3-Codex |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | September 28, 2026 | February 24, 2026 |
| Context window | 1M | 400K |
| Input $/Mtok | $2.00 | $1.75 |
| Output $/Mtok | $10.00 | $14.00 |
| Coding index | 87.3 | 60.0 |
| Independent measurements behind it | 5 | 3 |
| Cost per solved task | Not computable | $0.59 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 5.5 better than GPT-5.3-Codex for coding?
Pick Claude Sonnet 5.5 for coding: it scores 87.3 on the Vibe Coding Index against 60.0 for GPT-5.3-Codex. Pick GPT-5.3-Codex for work measured by Long context reasoning (AA-LCR), where it leads.
Which is cheaper, Claude Sonnet 5.5 or GPT-5.3-Codex?
Claude Sonnet 5.5 costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-5.3-Codex costs $1.75 and $14.00. Cost per solved task is known for GPT-5.3-Codex only.
Which has the bigger context window, Claude Sonnet 5.5 or GPT-5.3-Codex?
Claude Sonnet 5.5, with 1M tokens against 400K.
How many benchmarks is the Claude Sonnet 5.5 vs GPT-5.3-Codex comparison based on?
20 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5.5's coding index rests on 5 independent benchmarks and GPT-5.3-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.