Claude Fable 5.2 vs Claude Haiku 5.5
Claude Fable 5.2 leads Claude Haiku 5.5 on coding, 87.8 to 68.4 on the Vibe Coding Index, and Claude Haiku 5.5 costs 80.0x less per output token ($0.50 vs $40.00 per million). Updated November 14, 2026; 57 benchmarks have a result for both.
vs boards won of 57 shared
Claude Fable 5.2 or Claude Haiku 5.5: which to pick
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 68.4 for Claude Haiku 5.5, though on 4 benchmarks against 5.
Pick Claude Haiku 5.5 for output tokens 80.0x cheaper ($0.50 vs $40.00 per million).
Model AClaude Fable 5.2Anthropic87.8/1004 independent benchmarksNo cost per solved taskModel BClaude Haiku 5.5Anthropic68.4/1005 independent benchmarksNo cost per solved task
- Shared results
- 57
- Claude Fable 5.2 only
- 11
- Claude Haiku 5.5 only
- 50
- 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 68.4.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Fable 5.2
Claude Fable 5.2 leads, 64.6 against 36.5.
Same board, both measured
Web design
Design Arena: websites
Claude Fable 5.2
Claude Fable 5.2 leads, 1351 against 1253.
Same board, both measured
General
Vals Index
Claude Fable 5.2
Claude Fable 5.2 leads, 71.3% against 58.7%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 5.5
Claude Fable 5.2 $0.028, Claude Haiku 5.5 $0.0003 per turn.
List prices
At a glance
- Coding index
- Claude Fable 5.2 87.8 from 4 benchmarks, Claude Haiku 5.5 68.4 from 5 benchmarks.
- Widest category
- Knowledge, 48.7 points apart on average over 2 shared benchmarks.
- Widest single gap
- SimpleQA Verified: Claude Fable 5.2 94.0% against Claude Haiku 5.5 23.8%, 70.2 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.2 $40.00 against Claude Haiku 5.5 $0.50 per million output tokens, 80.0x apart.
- Context window
- Both take 1M tokens.
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 | Claude Haiku 5.5 | Ties |
|---|---|---|---|---|
| Coding | 15 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 10 | 0 | ||
| Reasoning | 11 | 0 | ||
| Math | 4 | 0 | ||
| Knowledge | 2 | 0 | ||
| Web design | 6 | 0 | ||
| General | 7 | 0 | ||
| All shared boards | 57 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index150
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| LiveBench coding | 79.2% | 77.6% | Claude Fable 5.2 |
| LMArena WebDev | 1838 | 1593 | Claude Fable 5.2 |
| Terminal-Bench 4 (Vals AI) | 65.2% | 36.4% | Claude Fable 5.2 |
| Vibe Code Bench (Vals AI) | 93.8% | 90.4% | Claude Fable 5.2 |
| Code migration (Vals AI) | Not measured | 44.6% | Only Claude Haiku 5.5 measured |
| ProgramBench (Vals AI) | 19.0% | 2.5% | Claude Fable 5.2 |
| IOI (Vals AI) | Not measured | 47.3% | Only Claude Haiku 5.5 measured |
| SWE-bench Multimodal (Vals AI) | 62.3% | 44.0% | Claude Fable 5.2 |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 20.4% | Only Claude Haiku 5.5 measured |
| CyberBench (Vals AI) | Not measured | 75.5% | Only Claude Haiku 5.5 measured |
| SciCode | 67.7% | 55.0% | Claude Fable 5.2 |
| Terminal-Bench 4.0 (Artificial Analysis run) | 61.6% | 32.8% | Claude Fable 5.2 |
| FrontierCode 2.0 | 49.1% | 34.9% | Claude Fable 5.2 |
| FrontierCode | Not measured | 46.4% | Only Claude Haiku 5.5 measured |
| FrontierSWE | 69.9% | 43.8% | Claude Fable 5.2 |
| MirrorCode | Not measured | 78.9% | Only Claude Haiku 5.5 measured |
| ALE-Bench | 2509.8 | 1587.0 | Claude Fable 5.2 |
| LMArena Text: coding | Not measured | 1454 | Only Claude Haiku 5.5 measured |
| LMArena Text: software and IT | Not measured | 1443 | Only Claude Haiku 5.5 measured |
| LMArena WebDev: React | 1915 | 1615 | Claude Fable 5.2 |
| LMArena WebDev: HTML | 1738 | 1564 | Claude Fable 5.2 |
| SciCode | Not measured | 9.2% | Only Claude Haiku 5.5 measured |
| SWE-Bench Pro V2 | Not measured | 87.2% | Only Claude Haiku 5.5 measured |
| GameBench 2 | 99.1 | 75.1 | Claude Fable 5.2 |
| Terminal-Bench 4.0 | Not measured | 40.0% | Only Claude Haiku 5.5 measured |
| CursorBench 4.0 | 60.0% | 48.4% | Claude Fable 5.2 |
| 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 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 64.6 | 36.5 | Claude Fable 5.2 |
| Epoch Capabilities Index | 173.4 | 160.4 | Claude Fable 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| Design Arena: agents building full-stack apps | 1402 | Not measured | Only Claude Fable 5.2 measured |
| Design Arena: agents building mobile apps | 1325 | Not measured | Only Claude Fable 5.2 measured |
| Design Arena: spreadsheets | 1434 | Not measured | Only Claude Fable 5.2 measured |
| LiveBench research | 94.5% | 84.3% | Claude Fable 5.2 |
| LiveBench browser | 86.9% | 69.5% | Claude Fable 5.2 |
| LiveBench long agentic | 82.9% | 47.9% | Claude Fable 5.2 |
| SREBench (Vals AI) | Not measured | 5.7% | Only Claude Haiku 5.5 measured |
| Finance Agent (Vals AI) | Not measured | 54.1% | Only Claude Haiku 5.5 measured |
| Tax Agent Bench (Vals AI) | 32.1% | 31.9% | Claude Fable 5.2 |
| Legal Research Bench (Vals AI) | 46.1% | 43.8% | Claude Fable 5.2 |
| Harvey's Legal Agent Benchmark (Vals AI) | 5.0% | 4.2% | Claude Fable 5.2 |
| Excel Modeling Benchmark (Vals AI) | Not measured | 59.0% | Only Claude Haiku 5.5 measured |
| BioMysteryBench (Vals AI) | 83.7% | 70.4% | Claude Fable 5.2 |
| Terminal-Bench-Science (Vals AI) | 55.7% | 10.0% | Claude Fable 5.2 |
| Vals Science Index | 63.7% | 38.5% | Claude Fable 5.2 |
| APEX-Agents | 80.1% | 56.1% | Claude Fable 5.2 |
| Remote Labor Index | 41.3% | Not measured | Only Claude Fable 5.2 measured |
| SpireClimb | 15.5% | Not measured | Only Claude Fable 5.2 measured |
| Vending-Bench 2 | Not measured | $3,602 | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.8% | 82.4% | Claude Fable 5.2 |
| MysteryMechanism (Vals AI) | 51.8% | 35.1% | Claude Fable 5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 74.3% | 44.4% | Claude Fable 5.2 |
| HLE-Diamond (Artificial Analysis run) | 80.2% | 29.6% | Claude Fable 5.2 |
| CritPt v2, hard subset (Artificial Analysis run) | 76.5% | 47.5% | Claude Fable 5.2 |
| GPQA Diamond (Epoch AI run) | 93.9% | 89.6% | Claude Fable 5.2 |
| ARC-AGI | 98.5% | 89.0% | Claude Fable 5.2 |
| ARC-AGI-2 | 93.8% | 61.3% | Claude Fable 5.2 |
| SimpleBench | 94.9% | Not measured | Only Claude Fable 5.2 measured |
| Chess puzzles | 79.0% | 55.0% | Claude Fable 5.2 |
| Mystery game puzzles | 90.0% | 30.0% | Claude Fable 5.2 |
| EBR-bench | 90.5% | 43.8% | Claude Fable 5.2 |
| LMArena Text: hard prompts | Not measured | 1418 | Only Claude Haiku 5.5 measured |
| LMArena Text: expert | Not measured | 1443 | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts in English | Not measured | 1422 | Only Claude Haiku 5.5 measured |
| Humanity's Last Exam (Scale run) | 72.4% | Not measured | Only Claude Fable 5.2 measured |
| GoBench | 2566 | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.7% | 98.9% | Claude Fable 5.2 |
| FrontierMath, tiers 1 to 3 | 95.1% | 75.1% | Claude Fable 5.2 |
| FrontierMath, tier 4 | 100.0% | 46.3% | Claude Fable 5.2 |
| ProofBench | 100.0% | 89.0% | Claude Fable 5.2 |
| LMArena Text: math | Not measured | 1436 | Only Claude Haiku 5.5 measured |
| LMArena Text: mathematical work | Not measured | 1437 | Only Claude Haiku 5.5 measured |
| MathArena | 82.8% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 51.5% | Only Claude Haiku 5.5 measured |
| AA-Omniscience | 66.8 | 12.3 | Claude Fable 5.2 |
| SimpleQA Verified | 94.0% | 23.8% | Claude Fable 5.2 |
| LMArena Text: science | Not measured | 1411 | Only Claude Haiku 5.5 measured |
| LMArena Text: medicine and healthcare | Not measured | 1367 | Only Claude Haiku 5.5 measured |
| LMArena Text: legal and government | Not measured | 1389 | Only Claude Haiku 5.5 measured |
| LMArena Text: business and finance | Not measured | 1400 | Only Claude Haiku 5.5 measured |
| FACTS Benchmark Suite | Not measured | 47.3% | Only Claude Haiku 5.5 measured |
| PRBench Finance | 47.1% | Not measured | Only Claude Fable 5.2 measured |
| PRBench Legal | 49.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1351 | 1253 | Claude Fable 5.2 |
| Design Arena: UI components | 1371 | 1271 | Claude Fable 5.2 |
| Design Arena: game dev | 1396 | 1316 | Claude Fable 5.2 |
| Design Arena: data viz | Not measured | 1277 | Only Claude Haiku 5.5 measured |
| Design Arena: 3D | 1517 | 1321 | Claude Fable 5.2 |
| Design Arena: all code categories | 1373 | 1278 | Claude Fable 5.2 |
| Design Arena: SVG | Not measured | 1193 | Only Claude Haiku 5.5 measured |
| Design Arena: ASCII art | Not measured | 1210 | Only Claude Haiku 5.5 measured |
| LiveBench design | 85.1% | 79.3% | Claude Fable 5.2 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| Vals Index | 71.3% | 58.7% | Claude Fable 5.2 |
| LiveBench data analysis | 81.5% | 53.1% | Claude Fable 5.2 |
| Public Benefits Bench (Vals AI) | Not measured | 63.2% | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | Not measured | 89.8% | Only Claude Haiku 5.5 measured |
| MedScribe (Vals AI) | Not measured | 89.5% | Only Claude Haiku 5.5 measured |
| Long context reasoning (AA-LCR) | 83.3% | 82.7% | Claude Fable 5.2 |
| GDPval-AA | 1831 | 1629 | Claude Fable 5.2 |
| DTBench | 99.2% | 95.0% | Claude Fable 5.2 |
| LMCA | 70.6% | 51.1% | Claude Fable 5.2 |
| Furniture assembly | 90.0% | 47.5% | Claude Fable 5.2 |
| LMArena Text | Not measured | 1398 | Only Claude Haiku 5.5 measured |
| LMArena Text: instruction following | Not measured | 1411 | Only Claude Haiku 5.5 measured |
| LMArena Text: creative writing | Not measured | 1337 | Only Claude Haiku 5.5 measured |
| LMArena Text: English | Not measured | 1406 | Only Claude Haiku 5.5 measured |
| LMArena Text: non-English | Not measured | 1385 | Only Claude Haiku 5.5 measured |
| LMArena Text: Chinese | Not measured | 1433 | Only Claude Haiku 5.5 measured |
| LMArena Text: German | Not measured | 1429 | Only Claude Haiku 5.5 measured |
| LMArena Text: Japanese | Not measured | 1374 | Only Claude Haiku 5.5 measured |
| LMArena Text: Korean | Not measured | 1382 | Only Claude Haiku 5.5 measured |
| LMArena Text: French | Not measured | 1427 | Only Claude Haiku 5.5 measured |
| LMArena Text: Spanish | Not measured | 1397 | Only Claude Haiku 5.5 measured |
| LMArena Text: Russian | Not measured | 1377 | Only Claude Haiku 5.5 measured |
| LMArena Text: Polish | Not measured | 1378 | Only Claude Haiku 5.5 measured |
| LMArena Text: multi-turn | Not measured | 1388 | Only Claude Haiku 5.5 measured |
| LMArena Text: longer queries | Not measured | 1395 | Only Claude Haiku 5.5 measured |
| LMArena Text: writing and language | Not measured | 1369 | Only Claude Haiku 5.5 measured |
| LMArena Text: entertainment and media | Not measured | 1351 | Only Claude Haiku 5.5 measured |
| MultiChallenge | Not measured | 67.7% | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.2 | Claude Haiku 5.5 | 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
Claude Haiku 5.5$0.0003Fits in one request
Claude Haiku 5.5 costs less
Repository review
50K input + 3K output tokens
Claude Fable 5.2$0.520Fits in one request
Claude Haiku 5.5$0.0065Fits in one request
Claude Haiku 5.5 costs less
Agent loop
200K input + 10K output tokens
Claude Fable 5.2$2.00Fits in one request
Claude Haiku 5.5$0.025Fits in one request
Claude Haiku 5.5 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 | Anthropic Claude Haiku 5.5 |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Weights | No public weights listed | No public weights listed |
| Released | November 9, 2026 | October 7, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $8.00 | $0.10 |
| Output $/Mtok | $40.00 | $0.50 |
| Coding index | 87.8 | 68.4 |
| 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 Claude Haiku 5.5 for coding?
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 68.4 for Claude Haiku 5.5, though on 4 benchmarks against 5. Pick Claude Haiku 5.5 for output tokens 80.0x cheaper ($0.50 vs $40.00 per million).
Which is cheaper, Claude Fable 5.2 or Claude Haiku 5.5?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; Claude Haiku 5.5 costs $0.10 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Fable 5.2 or Claude Haiku 5.5?
Neither: both take 1M tokens.
How many benchmarks is the Claude Fable 5.2 vs Claude Haiku 5.5 comparison based on?
57 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 Claude Haiku 5.5's on 5. Where only one model has a result, the page says so instead of naming a winner.