Claude Fable 5.1 vs GPT-5.4 Mini
Updated October 21, 2026. 77 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Claude Fable 5.1 for coding: it scores 89.1 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.
Pick GPT-5.4 Mini when output tokens cost 11.1x less, or when the benchmark that matters is SAGE (Vals AI), where it leads.
- Shared results
- 77
- Claude Fable 5.1 only
- 47
- GPT-5.4 Mini only
- 11
- 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
Claude Fable 5.1
Claude Fable 5.1 scores 89.1 against 28.2.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Fable 5.1
Claude Fable 5.1 leads, 53.4 against 24.1.
Same board, both measured
Agentic work
AA Agentic Index
Claude Fable 5.1
Claude Fable 5.1 leads, 57.9 against 17.9.
Same board, both measured
Reasoning
GPQA Diamond
Claude Fable 5.1
Claude Fable 5.1 leads, 93.4% against 83.1%.
Same board, both measured
Math
AIME
No call
Only GPT-5.4 Mini has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Claude Fable 5.1
Claude Fable 5.1 leads, 92.4% against 84.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Claude Fable 5.1 has a Design Arena: websites result, 1313.
Directional only
Long documents
Listed context window
Claude Fable 5.1
Claude Fable 5.1 takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.4 Mini
Claude Fable 5.1 $0.035, GPT-5.4 Mini $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 Mini has the number, $0.70.
Directional only
At a glance
- Coding index
- Claude Fable 5.1 89.1 from 2 benchmarks, GPT-5.4 Mini 28.2 from 1 benchmark.
- Widest category
- Math, 40.8 points apart on average over 6 shared benchmarks.
- Widest single gap
- ProofBench: Claude Fable 5.1 100.0% against GPT-5.4 Mini 21.0%, 79.0 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.1 $50.00 against GPT-5.4 Mini $4.50 per million output tokens, 11.1x apart.
- Context window
- Claude Fable 5.1 takes 1M tokens, GPT-5.4 Mini 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 Fable 5.1 | Bars | GPT-5.4 Mini | Ties |
|---|---|---|---|---|
| Coding | 16 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 0 | ||
| Reasoning | 13 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 8 | 0 | ||
| General | 26 | 1 | ||
| All shared boards | 76 | 1 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index160
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| LiveBench coding | 97.7% | Not measured | Only Claude Fable 5.1 measured |
| LMArena WebDev | 1743 | 1397 | Claude Fable 5.1 |
| AA Coding Index | 81.6 | 56.1 | Claude Fable 5.1 |
| LiveCodeBench (Vals AI) | 90.5% | 81.5% | Claude Fable 5.1 |
| SWE-bench Verified (Vals AI) | Not measured | 73.0% | Only GPT-5.4 Mini measured |
| Terminal-Bench 4 (Vals AI) | 58.1% | 2.5% | Claude Fable 5.1 |
| Vibe Code Bench (Vals AI) | 90.3% | 48.0% | Claude Fable 5.1 |
| Code migration (Vals AI) | 54.6% | 12.9% | Claude Fable 5.1 |
| ProgramBench (Vals AI) | 7.0% | 0.0% | Claude Fable 5.1 |
| IOI (Vals AI) | 90.8% | Not measured | Only Claude Fable 5.1 measured |
| Terminal-Bench 2.1 (Vals AI) | 85.0% | 54.7% | Claude Fable 5.1 |
| SWE-bench Multimodal (Vals AI) | 61.3% | Not measured | Only Claude Fable 5.1 measured |
| Vibe Code Bench 1-100 (Vals AI) | 28.0% | Not measured | Only Claude Fable 5.1 measured |
| SkillsBench (Vals AI) | 61.5% | Not measured | Only Claude Fable 5.1 measured |
| CyberBench (Vals AI) | 70.4% | Not measured | Only Claude Fable 5.1 measured |
| SciCode | 63.1% | 52.1% | Claude Fable 5.1 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 52.3% | Only GPT-5.4 Mini measured |
| FrontierCode | 50.9% | 27.0% | Claude Fable 5.1 |
| FrontierSWE | 56.3% | Not measured | Only Claude Fable 5.1 measured |
| GSO-Bench | 88.2% | Not measured | Only Claude Fable 5.1 measured |
| WeirdML | 92.9% | 60.3% | Claude Fable 5.1 |
| MirrorCode | 73.3% | Not measured | Only Claude Fable 5.1 measured |
| ALE-Bench | 2143.2 | 1188.6 | Claude Fable 5.1 |
| LMArena Text: coding | 1532 | 1438 | Claude Fable 5.1 |
| LMArena Text: software and IT | 1530 | 1436 | Claude Fable 5.1 |
| LMArena WebDev: React | 1792 | 1386 | Claude Fable 5.1 |
| LMArena WebDev: HTML | 1684 | 1419 | Claude Fable 5.1 |
| LMArena WebDev: from an image | 1722 | Not measured | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 10 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 53.4 | 24.1 | Claude Fable 5.1 |
| Epoch Capabilities Index | 166.5 | 148.7 | Claude Fable 5.1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 57.9 | 17.9 | Claude Fable 5.1 |
| Design Arena: agents building web apps | 1318 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: agents building full-stack apps | 1326 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: agents building mobile apps | 1267 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: agents building Godot games | 1327 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: PowerPoint slides | 1328 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: spreadsheets | 1374 | Not measured | Only Claude Fable 5.1 measured |
| LiveBench research | 82.0% | Not measured | Only Claude Fable 5.1 measured |
| LiveBench browser | 100.0% | Not measured | Only Claude Fable 5.1 measured |
| LiveBench long agentic | 80.8% | Not measured | Only Claude Fable 5.1 measured |
| SREBench (Vals AI) | 22.9% | Not measured | Only Claude Fable 5.1 measured |
| Finance Agent (Vals AI) | 58.9% | 45.4% | Claude Fable 5.1 |
| Tax Agent Bench (Vals AI) | 49.2% | 8.8% | Claude Fable 5.1 |
| Legal Research Bench (Vals AI) | 55.3% | 12.5% | Claude Fable 5.1 |
| Excel Modeling Benchmark (Vals AI) | 76.7% | 45.4% | Claude Fable 5.1 |
| Terminal-Bench-Science (Vals AI) | 40.0% | Not measured | Only Claude Fable 5.1 measured |
| Time Horizon Index (Vals AI) | 63.3% | Not measured | Only Claude Fable 5.1 measured |
| CUA-bench (Vals AI) | 13.2% | Not measured | Only Claude Fable 5.1 measured |
| Robo-bench (Vals AI) | 5.8% | Not measured | Only Claude Fable 5.1 measured |
| τ²-Bench Telecom | Not measured | 83.3% | Only GPT-5.4 Mini measured |
| APEX-Agents | 68.6% | Not measured | Only Claude Fable 5.1 measured |
| Remote Labor Index | 17.9% | Not measured | Only Claude Fable 5.1 measured |
| DeepResearch Bench | Not measured | 36.3% | Only GPT-5.4 Mini measured |
| SpireClimb | 2.0% | Not measured | Only Claude Fable 5.1 measured |
| Vending-Bench 2 | $5,422 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Search | 1246 | Not measured | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 13 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 93.4% | 83.1% | Claude Fable 5.1 |
| LiveBench reasoning | 91.7% | Not measured | Only Claude Fable 5.1 measured |
| MysteryMechanism (Vals AI) | 47.8% | Not measured | Only Claude Fable 5.1 measured |
| MMMU Pro (Vals AI) | 90.6% | 79.3% | Claude Fable 5.1 |
| GPQA Diamond (Artificial Analysis run) | 93.7% | 87.5% | Claude Fable 5.1 |
| Humanity's Last Exam (Artificial Analysis run) | 59.1% | 28.1% | Claude Fable 5.1 |
| GPQA Diamond (Epoch AI run) | Not measured | 86.9% | Only GPT-5.4 Mini measured |
| ARC-AGI | 97.5% | 63.7% | Claude Fable 5.1 |
| ARC-AGI-2 | 90.0% | 18.9% | Claude Fable 5.1 |
| Chess puzzles | 48.0% | 23.0% | Claude Fable 5.1 |
| Mystery game puzzles | 58.0% | 11.0% | Claude Fable 5.1 |
| EBR-bench | 57.1% | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: hard prompts | 1528 | 1424 | Claude Fable 5.1 |
| LMArena Text: expert | 1544 | 1435 | Claude Fable 5.1 |
| LMArena Text: hard prompts in English | 1522 | 1420 | Claude Fable 5.1 |
| LMArena Vision: diagrams | 1343 | 1266 | Claude Fable 5.1 |
| LMArena Vision: homework | 1345 | 1285 | Claude Fable 5.1 |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only GPT-5.4 Mini measured |
| OTIS Mock AIME | 100.0% | 88.9% | Claude Fable 5.1 |
| FrontierMath, tiers 1 to 3 | 90.2% | 51.2% | Claude Fable 5.1 |
| FrontierMath, tier 4 | 87.8% | 9.8% | Claude Fable 5.1 |
| ProofBench | 100.0% | 21.0% | Claude Fable 5.1 |
| LMArena Text: math | 1531 | 1418 | Claude Fable 5.1 |
| LMArena Text: mathematical work | 1541 | 1429 | Claude Fable 5.1 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 92.4% | 84.5% | Claude Fable 5.1 |
| LegalBench (Vals AI) | 88.5% | Not measured | Only Claude Fable 5.1 measured |
| CaseLaw (Vals AI) | Not measured | 51.7% | Only GPT-5.4 Mini measured |
| CorpFin (Vals AI) | Not measured | 60.9% | Only GPT-5.4 Mini measured |
| TaxEval (Vals AI) | 76.0% | 71.2% | Claude Fable 5.1 |
| MortgageTax (Vals AI) | 70.8% | 63.5% | Claude Fable 5.1 |
| MedCode (Vals AI) | 53.5% | Not measured | Only Claude Fable 5.1 measured |
| SimpleQA Verified | 70.8% | 29.4% | Claude Fable 5.1 |
| LMArena Text: science | 1532 | 1417 | Claude Fable 5.1 |
| LMArena Text: medicine and healthcare | 1531 | 1395 | Claude Fable 5.1 |
| LMArena Text: legal and government | 1514 | 1414 | Claude Fable 5.1 |
| LMArena Text: business and finance | 1493 | 1418 | Claude Fable 5.1 |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1313 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: UI components | 1338 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: game dev | 1382 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: data viz | 1344 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: 3D | 1393 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: all code categories | 1336 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: SVG | 1301 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: ASCII art | 1324 | Not measured | Only Claude Fable 5.1 measured |
| LiveBench design | 83.4% | Not measured | Only Claude Fable 5.1 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index261
| Benchmark | Claude Fable 5.1 | GPT-5.4 Mini | Leader |
|---|---|---|---|
| LiveBench data analysis | 80.3% | Not measured | Only Claude Fable 5.1 measured |
| Public Benefits Bench (Vals AI) | 74.9% | Not measured | Only Claude Fable 5.1 measured |
| SAGE (Vals AI) | 48.5% | 50.8% | GPT-5.4 Mini |
| MedScribe (Vals AI) | 91.3% | Not measured | Only Claude Fable 5.1 measured |
| Vals Multimodal Index | Not measured | 54.2% | Only GPT-5.4 Mini measured |
| IFBench | Not measured | 73.3% | Only GPT-5.4 Mini measured |
| Long context reasoning (AA-LCR) | 85.3% | 77.0% | Claude Fable 5.1 |
| DTBench | 97.6% | 80.0% | Claude Fable 5.1 |
| LMCA | 65.5% | 40.8% | Claude Fable 5.1 |
| Furniture assembly | 70.0% | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text | 1512 | 1412 | Claude Fable 5.1 |
| LMArena Text: instruction following | 1518 | 1405 | Claude Fable 5.1 |
| LMArena Text: creative writing | 1509 | 1370 | Claude Fable 5.1 |
| LMArena Vision | 1319 | 1245 | Claude Fable 5.1 |
| LMArena Text: English | 1506 | 1412 | Claude Fable 5.1 |
| LMArena Text: non-English | 1508 | 1405 | Claude Fable 5.1 |
| LMArena Text: Chinese | 1584 | 1446 | Claude Fable 5.1 |
| LMArena Text: German | 1499 | 1408 | Claude Fable 5.1 |
| LMArena Text: Japanese | 1562 | 1375 | Claude Fable 5.1 |
| LMArena Text: Korean | 1517 | 1370 | Claude Fable 5.1 |
| LMArena Text: French | 1523 | 1441 | Claude Fable 5.1 |
| LMArena Text: Spanish | 1520 | 1405 | Claude Fable 5.1 |
| LMArena Text: Russian | 1520 | 1417 | Claude Fable 5.1 |
| LMArena Text: Polish | 1525 | 1415 | Claude Fable 5.1 |
| LMArena Text: multi-turn | 1493 | 1429 | Claude Fable 5.1 |
| LMArena Text: longer queries | 1524 | 1408 | Claude Fable 5.1 |
| LMArena Text: writing and language | 1510 | 1393 | Claude Fable 5.1 |
| LMArena Text: entertainment and media | 1497 | 1373 | Claude Fable 5.1 |
| LMArena Vision: English | 1313 | 1244 | Claude Fable 5.1 |
| LMArena Vision: Chinese | 1391 | 1286 | Claude Fable 5.1 |
| LMArena Vision: reading text | 1327 | 1253 | Claude Fable 5.1 |
| LMArena Vision: humor | 1318 | 1235 | Claude Fable 5.1 |
| LMArena Vision: recognizing things | Not measured | 1218 | Only GPT-5.4 Mini measured |
| LMArena Vision: creative writing | 1330 | 1222 | Claude Fable 5.1 |
| 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 Fable 5.1 | GPT-5.4 Mini | 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-5.4 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5.4 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5.4 Mini 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 5.1 | OpenAI GPT-5.4 Mini |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | September 1, 2026 | March 17, 2026 |
| Context window | 1M | 400K |
| Input $/Mtok | $10.00 | $0.75 |
| Output $/Mtok | $50.00 | $4.50 |
| Coding index | 89.1 | 28.2 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | $0.70 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.1 better than GPT-5.4 Mini for coding?
Pick Claude Fable 5.1 for coding: it scores 89.1 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when output tokens cost 11.1x less, or when the benchmark that matters is SAGE (Vals AI), where it leads.
Which is cheaper, Claude Fable 5.1 or GPT-5.4 Mini?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Cost per solved task is known for GPT-5.4 Mini only.
Which has the bigger context window, Claude Fable 5.1 or GPT-5.4 Mini?
Claude Fable 5.1, with 1M tokens against 400K.
How many benchmarks is the Claude Fable 5.1 vs GPT-5.4 Mini comparison based on?
77 benchmarks have a result for both models as of October 21, 2026. Claude Fable 5.1's coding index rests on 2 independent benchmarks and GPT-5.4 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.