Claude Fable 5.2 vs GPT-6.1 Sol
Claude Fable 5.2 leads GPT-6.1 Sol on coding, 87.8 to 79.8 on the Vibe Coding Index, and GPT-6.1 Sol costs 4.0x less per output token ($10.00 vs $40.00 per million). Updated November 14, 2026; 63 benchmarks have a result for both.
vs boards won of 63 shared, 2 tied
Claude Fable 5.2 or GPT-6.1 Sol: which to pick
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 79.8 for GPT-6.1 Sol, though on 4 benchmarks against 5.
Pick GPT-6.1 Sol for output tokens 4.0x cheaper ($10.00 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).
Model AClaude Fable 5.2Anthropic87.8/1004 independent benchmarksNo cost per solved taskModel BGPT-6.1 SolOpenAI79.8/1005 independent benchmarksNo cost per solved task
- Shared results
- 63
- Claude Fable 5.2 only
- 5
- GPT-6.1 Sol only
- 66
- Like-for-like categories
- 8 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 Fable 5.2
Claude Fable 5.2 scores 87.8 against 79.8.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Fable 5.2
Claude Fable 5.2 leads, 64.6 against 54.6.
Same board, both measured
Web design
Design Arena: websites
Claude Fable 5.2
Claude Fable 5.2 leads, 1351 against 1316.
Same board, both measured
General
Vals Index
Claude Fable 5.2
Claude Fable 5.2 leads, 71.3% against 63.9%.
Same board, both measured
Long documents
Listed context window
GPT-6.1 Sol
GPT-6.1 Sol takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-6.1 Sol
Claude Fable 5.2 $0.028, GPT-6.1 Sol $0.0070 per turn.
List prices
At a glance
- Coding index
- Claude Fable 5.2 87.8 from 4 benchmarks, GPT-6.1 Sol 79.8 from 5 benchmarks.
- Widest category
- Reasoning, 10.7 points apart on average over 13 shared benchmarks.
- Widest single gap
- EBR-bench: Claude Fable 5.2 90.5% against GPT-6.1 Sol 54.3%, 36.2 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.2 $40.00 against GPT-6.1 Sol $10.00 per million output tokens, 4.0x apart.
- Context window
- Claude Fable 5.2 takes 1M tokens, GPT-6.1 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 Fable 5.2 | Bars | GPT-6.1 Sol | Ties |
|---|---|---|---|---|
| Coding | 10 | 3 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 10 | 3 | ||
| Reasoning | 9 | 3 | 1 tie | |
| Math | 3 | 1 | 1 tie | |
| Knowledge | 4 | 0 | ||
| Web design | 5 | 1 | ||
| General | 5 | 2 | ||
| All shared boards | 48 | 13 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index103
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| LiveBench coding | 79.2% | 82.1% | GPT-6.1 Sol |
| LMArena WebDev | 1838 | 1743 | Claude Fable 5.2 |
| Terminal-Bench 4 (Vals AI) | 65.2% | 55.0% | Claude Fable 5.2 |
| Vibe Code Bench (Vals AI) | 93.8% | 88.9% | Claude Fable 5.2 |
| Code migration (Vals AI) | Not measured | 65.1% | Only GPT-6.1 Sol measured |
| ProgramBench (Vals AI) | 19.0% | 3.0% | Claude Fable 5.2 |
| IOI (Vals AI) | Not measured | 96.9% | Only GPT-6.1 Sol measured |
| SWE-bench Multimodal (Vals AI) | 62.3% | 43.5% | Claude Fable 5.2 |
| CyberBench (Vals AI) | Not measured | 39.3% | Only GPT-6.1 Sol measured |
| SciCode | 67.7% | 55.8% | Claude Fable 5.2 |
| Terminal-Bench 4.0 (Artificial Analysis run) | 61.6% | 56.1% | Claude Fable 5.2 |
| FrontierCode 2.0 | 49.1% | 40.6% | Claude Fable 5.2 |
| FrontierCode | Not measured | 50.2% | Only GPT-6.1 Sol measured |
| FrontierSWE | 69.9% | Not measured | Only Claude Fable 5.2 measured |
| MirrorCode | Not measured | 61.1% | Only GPT-6.1 Sol measured |
| ALE-Bench | 2509.8 | 2743.8 | GPT-6.1 Sol |
| LMArena Text: coding | Not measured | 1486 | Only GPT-6.1 Sol measured |
| LMArena Text: software and IT | Not measured | 1478 | Only GPT-6.1 Sol measured |
| LMArena WebDev: React | 1915 | 1747 | Claude Fable 5.2 |
| LMArena WebDev: HTML | 1738 | 1794 | GPT-6.1 Sol |
| LMArena WebDev: from an image | Not measured | 1696 | Only GPT-6.1 Sol measured |
| SciCode | Not measured | 9.2% | Only GPT-6.1 Sol measured |
| SWE-Bench Pro V2 | Not measured | 96.1% | Only GPT-6.1 Sol measured |
| GameBench 2 | 99.1 | 92.0 | Claude Fable 5.2 |
| Terminal-Bench 4.0 | Not measured | 58.2% | Only GPT-6.1 Sol measured |
| CursorBench 4.0 | 60.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| AA Intelligence Index | 64.6 | 54.6 | Claude Fable 5.2 |
| Epoch Capabilities Index | 173.4 | 168.5 | Claude Fable 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index103
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1277 | Only GPT-6.1 Sol measured |
| Design Arena: agents building full-stack apps | 1402 | Not measured | Only Claude Fable 5.2 measured |
| Design Arena: agents building mobile apps | 1325 | 1229 | Claude Fable 5.2 |
| Design Arena: agents building Android apps | Not measured | 1190 | Only GPT-6.1 Sol measured |
| Design Arena: agents building games | Not measured | 1195 | Only GPT-6.1 Sol measured |
| Design Arena: HTML slides | Not measured | 1485 | Only GPT-6.1 Sol measured |
| Design Arena: PowerPoint slides | Not measured | 1304 | Only GPT-6.1 Sol measured |
| Design Arena: spreadsheets | 1434 | 1378 | Claude Fable 5.2 |
| LiveBench research | 94.5% | 90.0% | Claude Fable 5.2 |
| LiveBench browser | 86.9% | 93.3% | GPT-6.1 Sol |
| LiveBench long agentic | 82.9% | 65.6% | Claude Fable 5.2 |
| SREBench (Vals AI) | Not measured | 50.8% | Only GPT-6.1 Sol measured |
| Finance Agent (Vals AI) | Not measured | 52.0% | Only GPT-6.1 Sol measured |
| Tax Agent Bench (Vals AI) | 32.1% | 21.8% | Claude Fable 5.2 |
| Legal Research Bench (Vals AI) | 46.1% | 38.5% | Claude Fable 5.2 |
| Harvey's Legal Agent Benchmark (Vals AI) | 5.0% | 6.3% | GPT-6.1 Sol |
| Excel Modeling Benchmark (Vals AI) | Not measured | 70.8% | Only GPT-6.1 Sol measured |
| BioMysteryBench (Vals AI) | 83.7% | 79.6% | Claude Fable 5.2 |
| Terminal-Bench-Science (Vals AI) | 55.7% | 52.9% | Claude Fable 5.2 |
| Vals Science Index | 63.7% | 59.6% | Claude Fable 5.2 |
| Robo-bench (Vals AI) | Not measured | 28.3% | Only GPT-6.1 Sol measured |
| APEX-Agents | 80.1% | 60.0% | Claude Fable 5.2 |
| Remote Labor Index | 41.3% | Not measured | Only Claude Fable 5.2 measured |
| PostTrainBench | Not measured | 38.8% | Only GPT-6.1 Sol measured |
| SpireClimb | 15.5% | 23.8% | GPT-6.1 Sol |
| Vending-Bench 2 | Not measured | $12,861 | Only GPT-6.1 Sol measured |
| LMArena Search | Not measured | 1230 | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 17 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index93
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.8% | 92.6% | GPT-6.1 Sol |
| MysteryMechanism (Vals AI) | 51.8% | 46.4% | Claude Fable 5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 74.3% | 52.9% | Claude Fable 5.2 |
| HLE-Diamond (Artificial Analysis run) | 80.2% | 58.8% | Claude Fable 5.2 |
| CritPt v2, hard subset (Artificial Analysis run) | 76.5% | 69.5% | Claude Fable 5.2 |
| GPQA Diamond (Epoch AI run) | 93.9% | 95.4% | GPT-6.1 Sol |
| ARC-AGI | 98.5% | 98.5% | Tie |
| ARC-AGI-2 | 93.8% | 94.2% | GPT-6.1 Sol |
| SimpleBench | 94.9% | 82.9% | Claude Fable 5.2 |
| Chess puzzles | 79.0% | 68.0% | Claude Fable 5.2 |
| Mystery game puzzles | 90.0% | 80.0% | Claude Fable 5.2 |
| EBR-bench | 90.5% | 54.3% | Claude Fable 5.2 |
| LMArena Text: hard prompts | Not measured | 1466 | Only GPT-6.1 Sol measured |
| LMArena Text: expert | Not measured | 1498 | Only GPT-6.1 Sol measured |
| LMArena Text: hard prompts in English | Not measured | 1472 | Only GPT-6.1 Sol measured |
| LMArena Vision: diagrams | Not measured | 1312 | Only GPT-6.1 Sol measured |
| LMArena Vision: homework | Not measured | 1353 | Only GPT-6.1 Sol measured |
| Humanity's Last Exam (Scale run) | 72.4% | Not measured | Only Claude Fable 5.2 measured |
| GoBench | 2566 | 2378 | Claude Fable 5.2 |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.7% | 100.0% | GPT-6.1 Sol |
| FrontierMath, tiers 1 to 3 | 95.1% | 93.7% | Claude Fable 5.2 |
| FrontierMath, tier 4 | 100.0% | 100.0% | Tie |
| ProofBench | 100.0% | 99.0% | Claude Fable 5.2 |
| LMArena Text: math | Not measured | 1475 | Only GPT-6.1 Sol measured |
| LMArena Text: mathematical work | Not measured | 1498 | Only GPT-6.1 Sol measured |
| MathArena | 82.8% | 80.6% | Claude Fable 5.2 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 48.8% | Only GPT-6.1 Sol measured |
| AA-Omniscience | 66.8 | 42.4 | Claude Fable 5.2 |
| SimpleQA Verified | 94.0% | 73.9% | Claude Fable 5.2 |
| LMArena Text: science | Not measured | 1457 | Only GPT-6.1 Sol measured |
| LMArena Text: medicine and healthcare | Not measured | 1429 | Only GPT-6.1 Sol measured |
| LMArena Text: legal and government | Not measured | 1472 | Only GPT-6.1 Sol measured |
| LMArena Text: business and finance | Not measured | 1441 | Only GPT-6.1 Sol measured |
| FACTS Benchmark Suite | Not measured | 76.8% | Only GPT-6.1 Sol measured |
| PRBench Finance | 47.1% | 46.2% | Claude Fable 5.2 |
| PRBench Legal | 49.0% | 47.9% | Claude Fable 5.2 |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| Design Arena: websites | 1351 | 1316 | Claude Fable 5.2 |
| Design Arena: UI components | 1371 | 1353 | Claude Fable 5.2 |
| Design Arena: game dev | 1396 | 1407 | GPT-6.1 Sol |
| Design Arena: data viz | Not measured | 1276 | Only GPT-6.1 Sol measured |
| Design Arena: 3D | 1517 | 1426 | Claude Fable 5.2 |
| Design Arena: all code categories | 1373 | 1361 | Claude Fable 5.2 |
| Design Arena: SVG | Not measured | 1343 | Only GPT-6.1 Sol measured |
| LiveBench design | 85.1% | 79.6% | Claude Fable 5.2 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| Vals Index | 71.3% | 63.9% | Claude Fable 5.2 |
| LiveBench data analysis | 81.5% | 82.7% | GPT-6.1 Sol |
| Public Benefits Bench (Vals AI) | Not measured | 59.3% | Only GPT-6.1 Sol measured |
| SAGE (Vals AI) | Not measured | 90.5% | Only GPT-6.1 Sol measured |
| MedScribe (Vals AI) | Not measured | 86.5% | Only GPT-6.1 Sol measured |
| Long context reasoning (AA-LCR) | 83.3% | 84.0% | GPT-6.1 Sol |
| GDPval-AA | 1831 | 1607 | Claude Fable 5.2 |
| DTBench | 99.2% | 96.5% | Claude Fable 5.2 |
| LMCA | 70.6% | 62.8% | Claude Fable 5.2 |
| Furniture assembly | 90.0% | 80.0% | Claude Fable 5.2 |
| LMArena Text | Not measured | 1445 | Only GPT-6.1 Sol measured |
| LMArena Text: instruction following | Not measured | 1463 | Only GPT-6.1 Sol measured |
| LMArena Text: creative writing | Not measured | 1420 | Only GPT-6.1 Sol measured |
| LMArena Vision | Not measured | 1286 | Only GPT-6.1 Sol measured |
| LMArena Text: English | Not measured | 1451 | Only GPT-6.1 Sol measured |
| LMArena Text: non-English | Not measured | 1435 | Only GPT-6.1 Sol measured |
| LMArena Text: Chinese | Not measured | 1501 | Only GPT-6.1 Sol measured |
| LMArena Text: German | Not measured | 1449 | Only GPT-6.1 Sol measured |
| LMArena Text: Japanese | Not measured | 1427 | Only GPT-6.1 Sol measured |
| LMArena Text: Korean | Not measured | 1442 | Only GPT-6.1 Sol measured |
| LMArena Text: French | Not measured | 1449 | Only GPT-6.1 Sol measured |
| LMArena Text: Spanish | Not measured | 1439 | Only GPT-6.1 Sol measured |
| LMArena Text: Russian | Not measured | 1452 | Only GPT-6.1 Sol measured |
| LMArena Text: Polish | Not measured | 1446 | Only GPT-6.1 Sol measured |
| LMArena Text: multi-turn | Not measured | 1449 | Only GPT-6.1 Sol measured |
| LMArena Text: longer queries | Not measured | 1459 | Only GPT-6.1 Sol measured |
| LMArena Text: writing and language | Not measured | 1440 | Only GPT-6.1 Sol measured |
| LMArena Text: entertainment and media | Not measured | 1421 | Only GPT-6.1 Sol measured |
| LMArena Vision: English | Not measured | 1280 | Only GPT-6.1 Sol measured |
| LMArena Vision: Chinese | Not measured | 1340 | Only GPT-6.1 Sol measured |
| LMArena Vision: reading text | Not measured | 1291 | Only GPT-6.1 Sol measured |
| LMArena Vision: humor | Not measured | 1272 | Only GPT-6.1 Sol measured |
| LMArena Vision: creative writing | Not measured | 1292 | Only GPT-6.1 Sol measured |
| MultiChallenge | Not measured | 82.0% | Only GPT-6.1 Sol measured |
| EQ-Bench 4 | Not measured | 1272 | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.2 | GPT-6.1 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
Claude Fable 5.2$0.028Fits in one request
GPT-6.1 Sol$0.0070Fits in one request
GPT-6.1 Sol costs less
Repository review
50K input + 3K output tokens
Claude Fable 5.2$0.520Fits in one request
GPT-6.1 Sol$0.130Fits in one request
GPT-6.1 Sol costs less
Agent loop
200K input + 10K output tokens
Claude Fable 5.2$2.00Fits in one request
GPT-6.1 Sol$0.500Fits in one request
GPT-6.1 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 Fable 5.2 | OpenAI GPT-6.1 Sol |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | November 9, 2026 | September 29, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $8.00 | $2.00 |
| Output $/Mtok | $40.00 | $10.00 |
| Coding index | 87.8 | 79.8 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.2 better than GPT-6.1 Sol for coding?
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 79.8 for GPT-6.1 Sol, though on 4 benchmarks against 5. Pick GPT-6.1 Sol for output tokens 4.0x cheaper ($10.00 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).
Which is cheaper, Claude Fable 5.2 or GPT-6.1 Sol?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; GPT-6.1 Sol costs $2.00 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Fable 5.2 or GPT-6.1 Sol?
GPT-6.1 Sol, with 1.05M tokens against 1M.
How many benchmarks is the Claude Fable 5.2 vs GPT-6.1 Sol comparison based on?
63 benchmarks have a result for both models as of November 14, 2026. Claude Fable 5.2's coding index rests on 4 independent benchmarks and GPT-6.1 Sol's on 5. Where only one model has a result, the page says so instead of naming a winner.