Claude Fable 5.2 vs Claude Haiku 4.5
Claude Fable 5.2 leads Claude Haiku 4.5 on coding, 87.8 to 31.4 on the Vibe Coding Index, and Claude Haiku 4.5 costs 8.0x less per output token ($5.00 vs $40.00 per million). Updated November 14, 2026; 22 benchmarks have a result for both.
vs boards won of 22 shared
Claude Fable 5.2 or Claude Haiku 4.5: which to pick
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 31.4 for Claude Haiku 4.5.
Pick Claude Haiku 4.5 for output tokens 8.0x cheaper ($5.00 vs $40.00 per million).
Model AClaude Fable 5.2Anthropic87.8/1004 independent benchmarksNo cost per solved taskModel BClaude Haiku 4.5Anthropic31.4/1003 independent benchmarks$0.56 per solved task
- Shared results
- 22
- Claude Fable 5.2 only
- 46
- Claude Haiku 4.5 only
- 70
- 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 31.4.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Fable 5.2
Claude Fable 5.2 leads, 64.6 against 7.4.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Haiku 4.5 has a AA Agentic Index result, 8.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Haiku 4.5 has a GPQA Diamond result, 72.2%.
Directional only
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Haiku 4.5 has a MMLU Pro result, 78.7%.
Directional only
Web design
Design Arena: websites
Claude Fable 5.2
Claude Fable 5.2 leads, 1351 against 1114.
Same board, both measured
General
Vals Index
No call
Only Claude Fable 5.2 has a Vals Index result, 71.3%.
Directional only
Long documents
Listed context window
Claude Fable 5.2
Claude Fable 5.2 takes 1M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 4.5
Claude Fable 5.2 $0.028, Claude Haiku 4.5 $0.0035 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Haiku 4.5 has the number, $0.56.
Directional only
At a glance
- Coding index
- Claude Fable 5.2 87.8 from 4 benchmarks, Claude Haiku 4.5 31.4 from 3 benchmarks.
- Widest category
- Knowledge, 80.8 points apart on average over 1 shared benchmark.
- Widest single gap
- ARC-AGI-2: Claude Fable 5.2 93.8% against Claude Haiku 4.5 4.0%, 89.7 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.2 $40.00 against Claude Haiku 4.5 $5.00 per million output tokens, 8.0x apart.
- Context window
- Claude Fable 5.2 takes 1M tokens, Claude Haiku 4.5 200K.
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 4.5 | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 5 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 22 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 66.6% | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | Not measured | 64.7% | Only Claude Haiku 4.5 measured |
| LiveBench coding | 79.2% | Not measured | Only Claude Fable 5.2 measured |
| LMArena WebDev | 1838 | 1330 | Claude Fable 5.2 |
| AA Coding Index | Not measured | 43.9 | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Vals AI) | Not measured | 41.2% | Only Claude Haiku 4.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 66.6% | Only Claude Haiku 4.5 measured |
| Terminal-Bench 4 (Vals AI) | 65.2% | Not measured | Only Claude Fable 5.2 measured |
| Vibe Code Bench (Vals AI) | 93.8% | 11.4% | Claude Fable 5.2 |
| Code migration (Vals AI) | Not measured | 7.5% | Only Claude Haiku 4.5 measured |
| ProgramBench (Vals AI) | 19.0% | 0.0% | Claude Fable 5.2 |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 43.8% | Only Claude Haiku 4.5 measured |
| SWE-bench Multimodal (Vals AI) | 62.3% | Not measured | Only Claude Fable 5.2 measured |
| SciCode | 67.7% | Not measured | Only Claude Fable 5.2 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 61.6% | Not measured | Only Claude Fable 5.2 measured |
| FrontierCode 2.0 | 49.1% | Not measured | Only Claude Fable 5.2 measured |
| Terminal-Bench | Not measured | 35.5% | Only Claude Haiku 4.5 measured |
| FrontierSWE | 69.9% | Not measured | Only Claude Fable 5.2 measured |
| WeirdML | Not measured | 45.4% | Only Claude Haiku 4.5 measured |
| ALE-Bench | 2509.8 | Not measured | Only Claude Fable 5.2 measured |
| LMArena Text: coding | Not measured | 1453 | Only Claude Haiku 4.5 measured |
| LMArena Text: software and IT | Not measured | 1439 | Only Claude Haiku 4.5 measured |
| LMArena WebDev: React | 1915 | 1326 | Claude Fable 5.2 |
| LMArena WebDev: HTML | 1738 | 1318 | Claude Fable 5.2 |
| GameBench 2 | 99.1 | Not measured | Only Claude Fable 5.2 measured |
| Terminal-Bench 2.0 | Not measured | 35.5% | Only Claude Haiku 4.5 measured |
| CursorBench 4.0 | 60.0% | Not measured | Only Claude Fable 5.2 measured |
| ProgramBench | Not measured | 0.0% | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 64.6 | 7.4 | Claude Fable 5.2 |
| Epoch Capabilities Index | 173.4 | 142.8 | Claude Fable 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 8.0 | Only Claude Haiku 4.5 measured |
| 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% | Not measured | Only Claude Fable 5.2 measured |
| LiveBench browser | 86.9% | Not measured | Only Claude Fable 5.2 measured |
| LiveBench long agentic | 82.9% | Not measured | Only Claude Fable 5.2 measured |
| Finance Agent (Vals AI) | Not measured | 31.0% | Only Claude Haiku 4.5 measured |
| Tax Agent Bench (Vals AI) | 32.1% | 5.9% | Claude Fable 5.2 |
| Legal Research Bench (Vals AI) | 46.1% | 10.6% | Claude Fable 5.2 |
| Harvey's Legal Agent Benchmark (Vals AI) | 5.0% | Not measured | Only Claude Fable 5.2 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 22.7% | Only Claude Haiku 4.5 measured |
| BioMysteryBench (Vals AI) | 83.7% | Not measured | Only Claude Fable 5.2 measured |
| Terminal-Bench-Science (Vals AI) | 55.7% | Not measured | Only Claude Fable 5.2 measured |
| Vals Science Index | 63.7% | Not measured | Only Claude Fable 5.2 measured |
| APEX-Agents | 80.1% | Not measured | Only Claude Fable 5.2 measured |
| Remote Labor Index | 41.3% | Not measured | Only Claude Fable 5.2 measured |
| BALROG | Not measured | 31.2% | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | Not measured | 45.5% | Only Claude Haiku 4.5 measured |
| SpireClimb | 15.5% | Not measured | Only Claude Fable 5.2 measured |
| Vending-Bench 2 | Not measured | $459 | Only Claude Haiku 4.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 68.7% | Only Claude Haiku 4.5 measured |
| MCP Atlas | Not measured | 40.2% | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 72.2% | Only Claude Haiku 4.5 measured |
| LiveBench reasoning | 88.8% | Not measured | Only Claude Fable 5.2 measured |
| MysteryMechanism (Vals AI) | 51.8% | Not measured | Only Claude Fable 5.2 measured |
| MMMU Pro (Vals AI) | Not measured | 46.1% | Only Claude Haiku 4.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | 74.3% | Not measured | Only Claude Fable 5.2 measured |
| HLE-Diamond (Artificial Analysis run) | 80.2% | Not measured | Only Claude Fable 5.2 measured |
| CritPt v2, hard subset (Artificial Analysis run) | 76.5% | Not measured | Only Claude Fable 5.2 measured |
| GPQA Diamond (Epoch AI run) | 93.9% | 71.2% | Claude Fable 5.2 |
| ARC-AGI | 98.5% | 47.7% | Claude Fable 5.2 |
| ARC-AGI-2 | 93.8% | 4.0% | Claude Fable 5.2 |
| SimpleBench | 94.9% | Not measured | Only Claude Fable 5.2 measured |
| Chess puzzles | 79.0% | 8.0% | Claude Fable 5.2 |
| Mystery game puzzles | 90.0% | Not measured | Only Claude Fable 5.2 measured |
| EBR-bench | 90.5% | Not measured | Only Claude Fable 5.2 measured |
| LMArena Text: hard prompts | Not measured | 1420 | Only Claude Haiku 4.5 measured |
| LMArena Text: expert | Not measured | 1443 | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts in English | Not measured | 1435 | Only Claude Haiku 4.5 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 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| AIME | Not measured | 82.7% | Only Claude Haiku 4.5 measured |
| MGSM (Vals AI) | Not measured | 92.2% | Only Claude Haiku 4.5 measured |
| OTIS Mock AIME | 99.7% | 66.7% | Claude Fable 5.2 |
| FrontierMath, tiers 1 to 3 | 95.1% | Not measured | Only Claude Fable 5.2 measured |
| FrontierMath, tier 4 | 100.0% | Not measured | Only Claude Fable 5.2 measured |
| ProofBench | 100.0% | Not measured | Only Claude Fable 5.2 measured |
| MATH level 5 | Not measured | 96.4% | Only Claude Haiku 4.5 measured |
| LMArena Text: math | Not measured | 1397 | Only Claude Haiku 4.5 measured |
| LMArena Text: mathematical work | Not measured | 1429 | Only Claude Haiku 4.5 measured |
| MathArena | 82.8% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 78.7% | Only Claude Haiku 4.5 measured |
| LegalBench (Vals AI) | Not measured | 81.2% | Only Claude Haiku 4.5 measured |
| CaseLaw (Vals AI) | Not measured | 56.5% | Only Claude Haiku 4.5 measured |
| CorpFin (Vals AI) | Not measured | 60.6% | Only Claude Haiku 4.5 measured |
| TaxEval (Vals AI) | Not measured | 67.5% | Only Claude Haiku 4.5 measured |
| MortgageTax (Vals AI) | Not measured | 62.2% | Only Claude Haiku 4.5 measured |
| MedQA (Vals AI) | Not measured | 79.6% | Only Claude Haiku 4.5 measured |
| MedCode (Vals AI) | Not measured | 32.7% | Only Claude Haiku 4.5 measured |
| AA-Omniscience | 66.8 | Not measured | Only Claude Fable 5.2 measured |
| SimpleQA Verified | 94.0% | 13.2% | Claude Fable 5.2 |
| LMArena Text: science | Not measured | 1406 | Only Claude Haiku 4.5 measured |
| LMArena Text: medicine and healthcare | Not measured | 1394 | Only Claude Haiku 4.5 measured |
| LMArena Text: legal and government | Not measured | 1400 | Only Claude Haiku 4.5 measured |
| LMArena Text: business and finance | Not measured | 1399 | Only Claude Haiku 4.5 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 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1351 | 1114 | Claude Fable 5.2 |
| Design Arena: UI components | 1371 | 1090 | Claude Fable 5.2 |
| Design Arena: game dev | 1396 | 1086 | Claude Fable 5.2 |
| Design Arena: data viz | Not measured | 1121 | Only Claude Haiku 4.5 measured |
| Design Arena: 3D | 1517 | 1052 | Claude Fable 5.2 |
| Design Arena: all code categories | 1373 | 1104 | Claude Fable 5.2 |
| Design Arena: SVG | Not measured | 1015 | Only Claude Haiku 4.5 measured |
| Design Arena: ASCII art | Not measured | 1135 | Only Claude Haiku 4.5 measured |
| LiveBench design | 85.1% | Not measured | Only Claude Fable 5.2 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | Leader |
|---|---|---|---|
| Vals Index | 71.3% | Not measured | Only Claude Fable 5.2 measured |
| LiveBench data analysis | 81.5% | Not measured | Only Claude Fable 5.2 measured |
| Public Benefits Bench (Vals AI) | Not measured | 54.3% | Only Claude Haiku 4.5 measured |
| MedScribe (Vals AI) | Not measured | 85.2% | Only Claude Haiku 4.5 measured |
| Vals Multimodal Index | Not measured | 42.9% | Only Claude Haiku 4.5 measured |
| Long context reasoning (AA-LCR) | 83.3% | Not measured | Only Claude Fable 5.2 measured |
| GDPval-AA | 1831 | Not measured | Only Claude Fable 5.2 measured |
| DTBench | 99.2% | 73.6% | Claude Fable 5.2 |
| LMCA | 70.6% | 30.9% | Claude Fable 5.2 |
| Furniture assembly | 90.0% | Not measured | Only Claude Fable 5.2 measured |
| ExploitBench | Not measured | 13.7% | Only Claude Haiku 4.5 measured |
| LMArena Text | Not measured | 1396 | Only Claude Haiku 4.5 measured |
| LMArena Text: instruction following | Not measured | 1414 | Only Claude Haiku 4.5 measured |
| LMArena Text: creative writing | Not measured | 1371 | Only Claude Haiku 4.5 measured |
| LMArena Text: English | Not measured | 1414 | Only Claude Haiku 4.5 measured |
| LMArena Text: non-English | Not measured | 1376 | Only Claude Haiku 4.5 measured |
| LMArena Text: Chinese | Not measured | 1418 | Only Claude Haiku 4.5 measured |
| LMArena Text: German | Not measured | 1373 | Only Claude Haiku 4.5 measured |
| LMArena Text: Japanese | Not measured | 1340 | Only Claude Haiku 4.5 measured |
| LMArena Text: Korean | Not measured | 1344 | Only Claude Haiku 4.5 measured |
| LMArena Text: French | Not measured | 1411 | Only Claude Haiku 4.5 measured |
| LMArena Text: Spanish | Not measured | 1422 | Only Claude Haiku 4.5 measured |
| LMArena Text: Russian | Not measured | 1381 | Only Claude Haiku 4.5 measured |
| LMArena Text: Polish | Not measured | 1343 | Only Claude Haiku 4.5 measured |
| LMArena Text: multi-turn | Not measured | 1409 | Only Claude Haiku 4.5 measured |
| LMArena Text: longer queries | Not measured | 1426 | Only Claude Haiku 4.5 measured |
| LMArena Text: writing and language | Not measured | 1386 | Only Claude Haiku 4.5 measured |
| LMArena Text: entertainment and media | Not measured | 1369 | Only Claude Haiku 4.5 measured |
| LMArena Document | Not measured | 1420 | Only Claude Haiku 4.5 measured |
| MultiChallenge | Not measured | 50.5% | Only Claude Haiku 4.5 measured |
| EQ-Bench 4 | Not measured | 1053 | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.2 | Claude Haiku 4.5 | 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 4.5$0.0035Fits in one request
Claude Haiku 4.5 costs less
Repository review
50K input + 3K output tokens
Claude Fable 5.2$0.520Fits in one request
Claude Haiku 4.5$0.065Fits in one request
Claude Haiku 4.5 costs less
Agent loop
200K input + 10K output tokens
Claude Fable 5.2$2.00Fits in one request
Claude Haiku 4.5$0.250Exceeds the context window
Claude Haiku 4.5 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 4.5 |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Weights | No public weights listed | No public weights listed |
| Released | November 9, 2026 | October 15, 2025 |
| Context window | 1M | 200K |
| Input $/Mtok | $8.00 | $1.00 |
| Output $/Mtok | $40.00 | $5.00 |
| Coding index | 87.8 | 31.4 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | $0.56 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.2 better than Claude Haiku 4.5 for coding?
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 31.4 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for output tokens 8.0x cheaper ($5.00 vs $40.00 per million).
Which is cheaper, Claude Fable 5.2 or Claude Haiku 4.5?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; Claude Haiku 4.5 costs $1.00 and $5.00. Cost per solved task is known for Claude Haiku 4.5 only.
Which has the bigger context window, Claude Fable 5.2 or Claude Haiku 4.5?
Claude Fable 5.2, with 1M tokens against 200K.
How many benchmarks is the Claude Fable 5.2 vs Claude Haiku 4.5 comparison based on?
22 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 4.5's on 3. Where only one model has a result, the page says so instead of naming a winner.