Claude Opus 4.7 vs GPT-5.1
Updated October 21, 2026. 80 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GPT-5.1 for coding: it scores 53.3 on the Vibe Coding Index against 51.1 for Claude Opus 4.7.
Pick Claude Opus 4.7 when the context window is larger, 1M against 400K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.
- Shared results
- 80
- Claude Opus 4.7 only
- 21
- GPT-5.1 only
- 20
- Like-for-like categories
- 7 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
GPT-5.1
GPT-5.1 scores 53.3 against 51.1.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 4.7
Claude Opus 4.7 leads, 40.7 against 24.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Opus 4.7 has a AA Agentic Index result, 38.6.
Directional only
Reasoning
GPQA Diamond
Claude Opus 4.7
Claude Opus 4.7 leads, 90.2% against 86.6%.
Same board, both measured
Math
AIME
Claude Opus 4.7
Claude Opus 4.7 leads, 96.3% against 93.3%.
Same board, both measured
Knowledge
MMLU Pro
Claude Opus 4.7
Claude Opus 4.7 leads, 89.9% against 86.4%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5.1 has a Design Arena: websites result, 1187.
Directional only
Long documents
Listed context window
Claude Opus 4.7
Claude Opus 4.7 takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.1
Claude Opus 4.7 $0.018, GPT-5.1 $0.0063 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.1
Claude Opus 4.7 $2.95, GPT-5.1 $1.02.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.7 51.1 from 1 benchmark, GPT-5.1 53.3 from 2 benchmarks.
- Widest category
- Agentic work, 32.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- Vending-Bench 2: Claude Opus 4.7 $10,937 against GPT-5.1 $1,473, 59.1 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.7 $25.00 against GPT-5.1 $10.00 per million output tokens, 2.5x apart.
- Context window
- Claude Opus 4.7 takes 1M tokens, GPT-5.1 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 Opus 4.7 | Bars | GPT-5.1 | Ties |
|---|---|---|---|---|
| Coding | 13 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 14 | 1 | ||
| Math | 4 | 0 | ||
| Knowledge | 10 | 2 | ||
| General | 28 | 3 | ||
| All shared boards | 73 | 7 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index131
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 66.0% | Only GPT-5.1 measured |
| LMArena WebDev | 1558 | 1396 | Claude Opus 4.7 |
| AA Coding Index | 73.6 | 49.4 | Claude Opus 4.7 |
| LiveCodeBench (Vals AI) | 85.1% | 86.5% | GPT-5.1 |
| SWE-bench Verified (Vals AI) | 82.0% | 69.8% | Claude Opus 4.7 |
| Vibe Code Bench (Vals AI) | 71.0% | 24.6% | Claude Opus 4.7 |
| Code migration (Vals AI) | 43.9% | Not measured | Only Claude Opus 4.7 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Claude Opus 4.7 measured |
| Terminal-Bench 2.1 (Vals AI) | 68.5% | Not measured | Only Claude Opus 4.7 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 86.8% | Only GPT-5.1 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 54.5% | 45.5% | Claude Opus 4.7 |
| Terminal-Bench | 80.2% | 47.6% | Claude Opus 4.7 |
| FrontierCode | 38.5% | Not measured | Only Claude Opus 4.7 measured |
| GSO-Bench | 44.1% | 13.7% | Claude Opus 4.7 |
| WeirdML | 76.4% | 60.8% | Claude Opus 4.7 |
| MirrorCode | 31.1% | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text: coding | 1519 | 1453 | Claude Opus 4.7 |
| LMArena Text: software and IT | 1516 | 1454 | Claude Opus 4.7 |
| LMArena WebDev: React | 1560 | 1307 | Claude Opus 4.7 |
| LMArena WebDev: HTML | 1554 | 1405 | Claude Opus 4.7 |
| LMArena WebDev: from an image | 1577 | 1421 | Claude Opus 4.7 |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 40.7 | 24.7 | Claude Opus 4.7 |
| Epoch Capabilities Index | 156.8 | 149.8 | Claude Opus 4.7 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| AA Agentic Index | 38.6 | Not measured | Only Claude Opus 4.7 measured |
| Finance Agent (Vals AI) | 51.5% | Not measured | Only Claude Opus 4.7 measured |
| Tax Agent Bench (Vals AI) | 23.7% | Not measured | Only Claude Opus 4.7 measured |
| Legal Research Bench (Vals AI) | 38.5% | Not measured | Only Claude Opus 4.7 measured |
| Excel Modeling Benchmark (Vals AI) | 63.7% | Not measured | Only Claude Opus 4.7 measured |
| τ²-Bench Telecom | 88.6% | 81.9% | Claude Opus 4.7 |
| APEX-Agents | 49.2% | Not measured | Only Claude Opus 4.7 measured |
| OSWorld 2.0 | 18.2% | Not measured | Only Claude Opus 4.7 measured |
| DeepResearch Bench | Not measured | 42.8% | Only GPT-5.1 measured |
| PostTrainBench | 28.6% | Not measured | Only Claude Opus 4.7 measured |
| Vending-Bench 2 | $10,937 | $1,473 | Claude Opus 4.7 |
| LMArena Search | 1230 | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index141
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| GPQA Diamond | 90.2% | 86.6% | Claude Opus 4.7 |
| MMMU Pro (Vals AI) | 85.5% | 83.2% | Claude Opus 4.7 |
| GPQA Diamond (Artificial Analysis run) | 91.4% | 87.3% | Claude Opus 4.7 |
| Humanity's Last Exam (Artificial Analysis run) | 42.3% | 28.5% | Claude Opus 4.7 |
| GPQA Diamond (Epoch AI run) | 90.2% | 87.6% | Claude Opus 4.7 |
| ARC-AGI | 93.5% | 72.8% | Claude Opus 4.7 |
| ARC-AGI-2 | 75.8% | 17.6% | Claude Opus 4.7 |
| SimpleBench | 61.7% | 53.2% | Claude Opus 4.7 |
| Chess puzzles | 41.0% | 42.0% | GPT-5.1 |
| Mystery game puzzles | 28.0% | 19.0% | Claude Opus 4.7 |
| EBR-bench | 19.0% | Not measured | Only Claude Opus 4.7 measured |
| VPCT | Not measured | 58.7% | Only GPT-5.1 measured |
| LMArena Text: hard prompts | 1506 | 1457 | Claude Opus 4.7 |
| LMArena Text: expert | 1521 | 1470 | Claude Opus 4.7 |
| LMArena Text: hard prompts in English | 1508 | 1462 | Claude Opus 4.7 |
| LMArena Vision: diagrams | 1336 | 1264 | Claude Opus 4.7 |
| LMArena Vision: homework | 1337 | 1272 | Claude Opus 4.7 |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| AIME | 96.3% | 93.3% | Claude Opus 4.7 |
| MGSM (Vals AI) | Not measured | 93.0% | Only GPT-5.1 measured |
| AA Math Index | Not measured | 94.0 | Only GPT-5.1 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 94.0% | Only GPT-5.1 measured |
| OTIS Mock AIME | 97.8% | 88.6% | Claude Opus 4.7 |
| FrontierMath, tiers 1 to 3 | 70.2% | Not measured | Only Claude Opus 4.7 measured |
| FrontierMath, tier 4 | 31.7% | Not measured | Only Claude Opus 4.7 measured |
| ProofBench | 54.0% | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text: math | 1498 | 1446 | Claude Opus 4.7 |
| LMArena Text: mathematical work | 1509 | 1449 | Claude Opus 4.7 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index102
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| MMLU Pro | 89.9% | 86.4% | Claude Opus 4.7 |
| LegalBench (Vals AI) | 85.3% | 85.7% | GPT-5.1 |
| CaseLaw (Vals AI) | 68.4% | 73.4% | GPT-5.1 |
| CorpFin (Vals AI) | 66.1% | 63.8% | Claude Opus 4.7 |
| TaxEval (Vals AI) | 75.3% | 74.9% | Claude Opus 4.7 |
| MortgageTax (Vals AI) | 70.3% | 61.4% | Claude Opus 4.7 |
| MedQA (Vals AI) | Not measured | 96.4% | Only GPT-5.1 measured |
| MedCode (Vals AI) | 54.9% | 52.7% | Claude Opus 4.7 |
| MMLU Pro (Artificial Analysis run) | Not measured | 87.0% | Only GPT-5.1 measured |
| SimpleQA Verified | 51.7% | 48.0% | Claude Opus 4.7 |
| LMArena Text: science | 1508 | 1459 | Claude Opus 4.7 |
| LMArena Text: medicine and healthcare | 1495 | 1456 | Claude Opus 4.7 |
| LMArena Text: legal and government | 1504 | 1459 | Claude Opus 4.7 |
| LMArena Text: business and finance | 1490 | 1431 | Claude Opus 4.7 |
| Neither model has a result on the other 3 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1187 | Only GPT-5.1 measured |
| Design Arena: UI components | Not measured | 1166 | Only GPT-5.1 measured |
| Design Arena: game dev | Not measured | 1179 | Only GPT-5.1 measured |
| Design Arena: data viz | Not measured | 1204 | Only GPT-5.1 measured |
| Design Arena: 3D | Not measured | 1061 | Only GPT-5.1 measured |
| Design Arena: all code categories | Not measured | 1171 | Only GPT-5.1 measured |
| Design Arena: SVG | Not measured | 1149 | Only GPT-5.1 measured |
| Design Arena: ASCII art | Not measured | 1118 | Only GPT-5.1 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index283
| Benchmark | Claude Opus 4.7 | GPT-5.1 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 56.1% | 43.2% | Claude Opus 4.7 |
| MedScribe (Vals AI) | 83.0% | 88.1% | GPT-5.1 |
| Vals Multimodal Index | 67.4% | Not measured | Only Claude Opus 4.7 measured |
| IFBench | 58.6% | 72.9% | GPT-5.1 |
| Long context reasoning (AA-LCR) | 78.7% | 80.0% | GPT-5.1 |
| DTBench | 94.7% | 90.1% | Claude Opus 4.7 |
| LMCA | 52.2% | 43.9% | Claude Opus 4.7 |
| CL-bench | Not measured | 23.7% | Only GPT-5.1 measured |
| Furniture assembly | 33.3% | Not measured | Only Claude Opus 4.7 measured |
| ExploitBench | 26.5% | Not measured | Only Claude Opus 4.7 measured |
| CL-bench Life | Not measured | 17.3% | Only GPT-5.1 measured |
| LMArena Text | 1490 | 1443 | Claude Opus 4.7 |
| LMArena Text: instruction following | 1498 | 1443 | Claude Opus 4.7 |
| LMArena Text: creative writing | 1486 | 1427 | Claude Opus 4.7 |
| LMArena Vision | 1317 | 1250 | Claude Opus 4.7 |
| LMArena Text: English | 1496 | 1451 | Claude Opus 4.7 |
| LMArena Text: non-English | 1480 | 1431 | Claude Opus 4.7 |
| LMArena Text: Chinese | 1531 | 1495 | Claude Opus 4.7 |
| LMArena Text: German | 1495 | 1438 | Claude Opus 4.7 |
| LMArena Text: Japanese | 1474 | 1453 | Claude Opus 4.7 |
| LMArena Text: Korean | 1464 | 1401 | Claude Opus 4.7 |
| LMArena Text: French | 1503 | 1450 | Claude Opus 4.7 |
| LMArena Text: Spanish | 1494 | 1433 | Claude Opus 4.7 |
| LMArena Text: Russian | 1494 | 1435 | Claude Opus 4.7 |
| LMArena Text: Polish | 1489 | 1440 | Claude Opus 4.7 |
| LMArena Text: multi-turn | 1505 | 1450 | Claude Opus 4.7 |
| LMArena Text: longer queries | 1505 | 1448 | Claude Opus 4.7 |
| LMArena Text: writing and language | 1492 | 1428 | Claude Opus 4.7 |
| LMArena Text: entertainment and media | 1474 | 1415 | Claude Opus 4.7 |
| LMArena Vision: English | 1322 | 1252 | Claude Opus 4.7 |
| LMArena Vision: Chinese | 1371 | 1270 | Claude Opus 4.7 |
| LMArena Vision: reading text | 1327 | 1255 | Claude Opus 4.7 |
| LMArena Vision: humor | 1309 | 1263 | Claude Opus 4.7 |
| LMArena Vision: captioning | Not measured | 1252 | Only GPT-5.1 measured |
| LMArena Vision: recognizing things | 1278 | 1232 | Claude Opus 4.7 |
| LMArena Vision: creative writing | 1326 | 1266 | Claude Opus 4.7 |
| LMArena Document | 1495 | 1403 | Claude Opus 4.7 |
| 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 Opus 4.7 | GPT-5.1 | 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-5.1 costs less
Repository review
50K input + 3K output tokens
GPT-5.1 costs less
Agent loop
200K input + 10K output tokens
GPT-5.1 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 Opus 4.7 | OpenAI GPT-5.1 |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | April 16, 2026 | November 13, 2025 |
| Context window | 1M | 400K |
| Input $/Mtok | $5.00 | $1.25 |
| Output $/Mtok | $25.00 | $10.00 |
| Coding index | 51.1 | 53.3 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $2.95 | $1.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.7 better than GPT-5.1 for coding?
Pick GPT-5.1 for coding: it scores 53.3 on the Vibe Coding Index against 51.1 for Claude Opus 4.7. Pick Claude Opus 4.7 when the context window is larger, 1M against 400K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.
Which is cheaper, Claude Opus 4.7 or GPT-5.1?
Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.1 costs $1.25 and $10.00. Per solved SWE-bench Verified task, Claude Opus 4.7 costs $2.95 and GPT-5.1 $1.02.
Which has the bigger context window, Claude Opus 4.7 or GPT-5.1?
Claude Opus 4.7, with 1M tokens against 400K.
How many benchmarks is the Claude Opus 4.7 vs GPT-5.1 comparison based on?
80 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.7's coding index rests on 1 independent benchmark and GPT-5.1's on 2. Where only one model has a result, the page says so instead of naming a winner.