Claude Sonnet 4.6 vs GPT-6.2 Sol
GPT-6.2 Sol leads Claude Sonnet 4.6 on coding, 83.1 to 55.0 on the Vibe Coding Index, and GPT-6.2 Sol costs 1.5x less per output token ($10.00 vs $15.00 per million). Updated November 22, 2026; 31 benchmarks have a result for both.
Claude Sonnet 4.6 or GPT-6.2 Sol: which to pick
Pick GPT-6.2 Sol for coding: it scores 83.1 on the Vibe Coding Index against 55.0 for Claude Sonnet 4.6.
Pick Claude Sonnet 4.6 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 31
- Claude Sonnet 4.6 only
- 86
- GPT-6.2 Sol only
- 25
- 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
GPT-6.2 Sol
GPT-6.2 Sol scores 83.1 against 55.0.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only GPT-6.2 Sol has a AA Intelligence Index result, 57.3.
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
No call
Only Claude Sonnet 4.6 has a Design Arena: websites result, 1272.
Directional only
General
Vals Index
No call
Only GPT-6.2 Sol has a Vals Index result, 66.1%.
Directional only
Long documents
Listed context window
GPT-6.2 Sol
GPT-6.2 Sol takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-6.2 Sol
Claude Sonnet 4.6 $0.011, GPT-6.2 Sol $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 55.0 from 4 benchmarks, GPT-6.2 Sol 83.1 from 4 benchmarks.
- Widest category
- Web design, 26.4 points apart on average over 3 shared benchmarks.
- Widest single gap
- Terminal-Bench 4.0 (Artificial Analysis run): Claude Sonnet 4.6 3.0% against GPT-6.2 Sol 60.1%, 57.1 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.6 $15.00 against GPT-6.2 Sol $10.00 per million output tokens, 1.5x apart.
- Context window
- Claude Sonnet 4.6 takes 1M tokens, GPT-6.2 Sol 1.05M.
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 | GPT-6.2 Sol | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Agentic work | 3 | 1 | ||
| Reasoning | 2 | 2 | ||
| Knowledge | 2 | 0 | ||
| Web design | 0 | 3 | ||
| General | 11 | 0 | ||
| All shared boards | 20 | 11 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index25
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 83.7% | Only GPT-6.2 Sol measured |
| LMArena WebDev | 1522 | 1754 | GPT-6.2 Sol |
| 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 | 60.6% | Only GPT-6.2 Sol measured |
| Vibe Code Bench (Vals AI) | 55.8% | 87.6% | GPT-6.2 Sol |
| Code migration (Vals AI) | 39.9% | Not measured | Only Claude Sonnet 4.6 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench 2.1 (Vals AI) | 57.3% | Not measured | Only Claude Sonnet 4.6 measured |
| SkillsBench (Vals AI) | 49.0% | Not measured | Only Claude Sonnet 4.6 measured |
| SciCode | 50.1% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 53.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 3.0% | 60.1% | GPT-6.2 Sol |
| FrontierCode 2.0 | Not measured | 44.4% | Only GPT-6.2 Sol measured |
| Terminal-Bench | 53.4% | Not measured | Only Claude Sonnet 4.6 measured |
| FrontierCode | 24.3% | Not measured | Only Claude Sonnet 4.6 measured |
| WeirdML | 66.1% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: coding | 1503 | 1440 | Claude Sonnet 4.6 |
| LMArena Text: software and IT | 1491 | 1434 | Claude Sonnet 4.6 |
| LMArena WebDev: React | 1511 | 1761 | GPT-6.2 Sol |
| LMArena WebDev: HTML | 1526 | 1840 | GPT-6.2 Sol |
| LMArena WebDev: from an image | 1529 | Not measured | Only Claude Sonnet 4.6 measured |
| SWE Atlas: Codebase QnA | 31.2% | Not measured | Only Claude Sonnet 4.6 measured |
| SWE Atlas: Refactoring | 32.2% | Not measured | Only Claude Sonnet 4.6 measured |
| SWE Atlas: Test Writing | 31.8% | Not measured | Only Claude Sonnet 4.6 measured |
| GameBench 2 | Not measured | 94.4 | Only GPT-6.2 Sol measured |
| Terminal-Bench 2.0 | 53.4% | Not measured | Only Claude Sonnet 4.6 measured |
| ProgramBench | 0.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 57.3 | Only GPT-6.2 Sol measured |
| Epoch Capabilities Index | 152.8 | Not measured | Only Claude Sonnet 4.6 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1158 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building full-stack apps | 1190 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building mobile apps | 1204 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building Android apps | 1181 | 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 | 1118 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench research | Not measured | 90.1% | Only GPT-6.2 Sol measured |
| LiveBench browser | Not measured | 88.2% | Only GPT-6.2 Sol measured |
| LiveBench long agentic | Not measured | 63.6% | Only GPT-6.2 Sol measured |
| Finance Agent (Vals AI) | 51.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Tax Agent Bench (Vals AI) | 25.8% | 24.8% | Claude Sonnet 4.6 |
| Legal Research Bench (Vals AI) | 38.5% | 37.0% | Claude Sonnet 4.6 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 12.1% | Only GPT-6.2 Sol measured |
| Excel Modeling Benchmark (Vals AI) | 60.2% | Not measured | Only Claude Sonnet 4.6 measured |
| BioMysteryBench (Vals AI) | Not measured | 77.8% | Only GPT-6.2 Sol measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 58.6% | Only GPT-6.2 Sol measured |
| Vals Science Index | Not measured | 57.8% | Only GPT-6.2 Sol measured |
| τ²-Bench Telecom | 79.5% | Not measured | Only Claude Sonnet 4.6 measured |
| APEX-Agents | 43.0% | 66.6% | GPT-6.2 Sol |
| 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 |
| Vending-Bench 2 | $7,204 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Search | 1220 | 1179 | Claude Sonnet 4.6 |
| MCP Atlas | 69.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 19 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench reasoning | Not measured | 90.6% | Only GPT-6.2 Sol measured |
| MysteryMechanism (Vals AI) | Not measured | 36.9% | Only GPT-6.2 Sol 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% | Not measured | Only Claude Sonnet 4.6 measured |
| HLE-Diamond (Artificial Analysis run) | Not measured | 64.0% | Only GPT-6.2 Sol measured |
| CritPt v2, hard subset (Artificial Analysis run) | Not measured | 64.0% | Only GPT-6.2 Sol measured |
| GPQA Diamond (Epoch AI run) | 87.4% | Not measured | Only Claude Sonnet 4.6 measured |
| ARC-AGI | 86.5% | 97.5% | GPT-6.2 Sol |
| ARC-AGI-2 | 60.4% | 85.8% | GPT-6.2 Sol |
| SimpleBench | Not measured | 69.9% | Only GPT-6.2 Sol measured |
| Chess puzzles | 23.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Mystery game puzzles | 16.0% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: hard prompts | 1484 | 1419 | Claude Sonnet 4.6 |
| LMArena Text: expert | 1500 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: hard prompts in English | 1494 | 1413 | Claude Sonnet 4.6 |
| LMArena Vision: diagrams | 1305 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: homework | 1311 | Not measured | Only Claude Sonnet 4.6 measured |
| Kagi LLM Benchmark | Not measured | 67.0% | Only GPT-6.2 Sol measured |
| Humanity's Last Exam (Scale run) | Not measured | 56.5% | Only GPT-6.2 Sol measured |
| Neither model has a result on the other 5 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| AIME | 92.3% | Not measured | Only Claude Sonnet 4.6 measured |
| OTIS Mock AIME | 85.8% | Not measured | Only Claude Sonnet 4.6 measured |
| ProofBench | 45.0% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: math | 1461 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: mathematical work | 1482 | Not measured | Only Claude Sonnet 4.6 measured |
| MathArena | Not measured | 91.2% | Only GPT-6.2 Sol measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | 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 |
| AA-Omniscience | Not measured | 40.4 | Only GPT-6.2 Sol measured |
| SimpleQA Verified | 35.5% | Not measured | Only Claude Sonnet 4.6 measured |
| GeoBench | 73.0% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: science | 1475 | 1432 | Claude Sonnet 4.6 |
| LMArena Text: medicine and healthcare | 1451 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: legal and government | 1469 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: business and finance | 1463 | 1383 | Claude Sonnet 4.6 |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| Design Arena: websites | 1272 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: UI components | 1255 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: game dev | 1231 | 1437 | GPT-6.2 Sol |
| Design Arena: data viz | 1272 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: 3D | 1201 | 1482 | GPT-6.2 Sol |
| Design Arena: all code categories | 1258 | 1405 | GPT-6.2 Sol |
| Design Arena: SVG | 1181 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: ASCII art | 1221 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench design | Not measured | 80.0% | Only GPT-6.2 Sol measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | Leader |
|---|---|---|---|
| Vals Index | Not measured | 66.1% | Only GPT-6.2 Sol measured |
| LiveBench data analysis | Not measured | 81.1% | Only GPT-6.2 Sol measured |
| Public Benefits Bench (Vals AI) | 62.5% | Not measured | Only Claude Sonnet 4.6 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% | Not measured | Only Claude Sonnet 4.6 measured |
| GDPval-AA | 1240 | Not measured | Only Claude Sonnet 4.6 measured |
| DTBench | 89.9% | Not measured | Only Claude Sonnet 4.6 measured |
| LMCA | 46.5% | Not measured | Only Claude Sonnet 4.6 measured |
| ExploitBench | 23.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text | 1458 | 1414 | Claude Sonnet 4.6 |
| LMArena Text: instruction following | 1476 | 1434 | Claude Sonnet 4.6 |
| LMArena Text: creative writing | 1435 | 1403 | Claude Sonnet 4.6 |
| LMArena Vision | 1282 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: English | 1473 | 1419 | Claude Sonnet 4.6 |
| LMArena Text: non-English | 1439 | 1405 | Claude Sonnet 4.6 |
| LMArena Text: Chinese | 1490 | 1434 | Claude Sonnet 4.6 |
| LMArena Text: German | 1429 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: Japanese | 1420 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: Korean | 1414 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: French | 1465 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: Spanish | 1463 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: Russian | 1439 | 1401 | Claude Sonnet 4.6 |
| LMArena Text: Polish | 1441 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: multi-turn | 1463 | 1420 | Claude Sonnet 4.6 |
| LMArena Text: longer queries | 1479 | 1427 | Claude Sonnet 4.6 |
| LMArena Text: writing and language | 1443 | 1420 | Claude Sonnet 4.6 |
| LMArena Text: entertainment and media | 1430 | 1408 | Claude Sonnet 4.6 |
| LMArena Vision: English | 1298 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: Chinese | 1310 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: reading text | 1295 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: humor | 1251 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: recognizing things | 1196 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: creative writing | 1273 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Document | 1482 | Not measured | Only Claude Sonnet 4.6 measured |
| MultiChallenge | Not measured | 72.0% | Only GPT-6.2 Sol measured |
| EQ-Bench 4 | 1197 | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.6 | GPT-6.2 Sol | 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
GPT-6.2 Sol costs less
Repository review
50K input + 3K output tokens
GPT-6.2 Sol costs less
Agent loop
200K input + 10K output tokens
GPT-6.2 Sol 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 | OpenAI GPT-6.2 Sol |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | February 17, 2026 | November 17, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $3.00 | $2.00 |
| Output $/Mtok | $15.00 | $10.00 |
| Coding index | 55.0 | 83.1 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | $1.68 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.6 better than GPT-6.2 Sol for coding?
Pick GPT-6.2 Sol for coding: it scores 83.1 on the Vibe Coding Index against 55.0 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Claude Sonnet 4.6 or GPT-6.2 Sol?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-6.2 Sol 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 GPT-6.2 Sol?
GPT-6.2 Sol, with 1.05M tokens against 1M.
How many benchmarks is the Claude Sonnet 4.6 vs GPT-6.2 Sol comparison based on?
31 benchmarks have a result for both models as of November 22, 2026. Claude Sonnet 4.6's coding index rests on 4 independent benchmarks and GPT-6.2 Sol's on 4. Where only one model has a result, the page says so instead of naming a winner.