Claude Fable 5.2 vs Qwen3.8 Max (0902)
Claude Fable 5.2 leads Qwen3.8 Max (0902) on coding, 87.8 to 67.3 on the Vibe Coding Index, and Qwen3.8 Max (0902) costs 6.7x less per output token ($6.00 vs $40.00 per million). Updated November 14, 2026; 55 benchmarks have a result for both.
Claude Fable 5.2 or Qwen3.8 Max (0902): which to pick
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 67.3 for Qwen3.8 Max (0902), though on 4 benchmarks against 5.
Pick Qwen3.8 Max (0902) for output tokens 6.7x cheaper ($6.00 vs $40.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
- Shared results
- 55
- Claude Fable 5.2 only
- 13
- Qwen3.8 Max (0902) only
- 73
- 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 67.3.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Fable 5.2
Claude Fable 5.2 leads, 64.6 against 33.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.8 Max (0902) has a AA Agentic Index result, 56.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.8 Max (0902) has a GPQA Diamond result, 93.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.8 Max (0902) has a MMLU Pro result, 88.6%.
Directional only
Web design
Design Arena: websites
Claude Fable 5.2
Claude Fable 5.2 leads, 1351 against 1269.
Same board, both measured
General
Vals Index
Claude Fable 5.2
Claude Fable 5.2 leads, 71.3% against 59.1%.
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
Qwen3.8 Max (0902)
Claude Fable 5.2 $0.028, Qwen3.8 Max (0902) $0.0050 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.8 Max (0902) has the number, $1.32.
Directional only
At a glance
- Coding index
- Claude Fable 5.2 87.8 from 4 benchmarks, Qwen3.8 Max (0902) 67.3 from 5 benchmarks.
- Widest category
- Knowledge, 37.4 points apart on average over 2 shared benchmarks.
- Widest single gap
- Furniture assembly: Claude Fable 5.2 90.0% against Qwen3.8 Max (0902) 20.0%, 70.0 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.2 $40.00 against Qwen3.8 Max (0902) $6.00 per million output tokens, 6.7x 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 | Qwen3.8 Max (0902) | Ties |
|---|---|---|---|---|
| Coding | 14 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 8 | 3 | ||
| Reasoning | 8 | 0 | ||
| Math | 4 | 1 | ||
| Knowledge | 2 | 0 | ||
| Web design | 6 | 0 | ||
| General | 7 | 0 | ||
| All shared boards | 51 | 4 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index140
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| LiveBench coding | 79.2% | 60.9% | Claude Fable 5.2 |
| LMArena WebDev | 1838 | 1676 | Claude Fable 5.2 |
| AA Coding Index | Not measured | 76.2 | Only Qwen3.8 Max (0902) measured |
| LiveCodeBench (Vals AI) | Not measured | 87.8% | Only Qwen3.8 Max (0902) measured |
| SWE-bench Verified (Vals AI) | Not measured | 85.6% | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 4 (Vals AI) | 65.2% | 38.9% | Claude Fable 5.2 |
| Vibe Code Bench (Vals AI) | 93.8% | 77.1% | Claude Fable 5.2 |
| Code migration (Vals AI) | Not measured | 24.0% | Only Qwen3.8 Max (0902) measured |
| ProgramBench (Vals AI) | 19.0% | 0.0% | Claude Fable 5.2 |
| IOI (Vals AI) | Not measured | 68.9% | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 67.4% | Only Qwen3.8 Max (0902) measured |
| SWE-bench Multimodal (Vals AI) | 62.3% | 42.5% | Claude Fable 5.2 |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 24.8% | Only Qwen3.8 Max (0902) measured |
| SkillsBench (Vals AI) | Not measured | 42.0% | Only Qwen3.8 Max (0902) measured |
| CyberBench (Vals AI) | Not measured | 28.6% | Only Qwen3.8 Max (0902) measured |
| SciCode | 67.7% | 53.2% | Claude Fable 5.2 |
| Terminal-Bench 4.0 (Artificial Analysis run) | 61.6% | 38.9% | Claude Fable 5.2 |
| FrontierCode 2.0 | 49.1% | 23.4% | Claude Fable 5.2 |
| FrontierSWE | 69.9% | 17.8% | Claude Fable 5.2 |
| MirrorCode | Not measured | 52.2% | Only Qwen3.8 Max (0902) measured |
| ALE-Bench | 2509.8 | 1679.1 | Claude Fable 5.2 |
| LMArena Text: coding | Not measured | 1502 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: software and IT | Not measured | 1500 | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev: React | 1915 | 1698 | Claude Fable 5.2 |
| LMArena WebDev: HTML | 1738 | 1654 | Claude Fable 5.2 |
| LMArena WebDev: from an image | Not measured | 1638 | Only Qwen3.8 Max (0902) measured |
| GameBench 2 | 99.1 | 69.6 | Claude Fable 5.2 |
| Terminal-Bench 4.0 | Not measured | 27.0% | Only Qwen3.8 Max (0902) measured |
| CursorBench 4.0 | 60.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| AA Intelligence Index | 64.6 | 33.7 | Claude Fable 5.2 |
| Epoch Capabilities Index | 173.4 | 157.6 | Claude Fable 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index83
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 56.0 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building web apps | Not measured | 1278 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building full-stack apps | 1402 | 1279 | Claude Fable 5.2 |
| Design Arena: agents building mobile apps | 1325 | 1223 | Claude Fable 5.2 |
| Design Arena: agents building Android apps | Not measured | 1196 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Godot games | Not measured | 1215 | Only Qwen3.8 Max (0902) measured |
| Design Arena: PowerPoint slides | Not measured | 1252 | Only Qwen3.8 Max (0902) measured |
| Design Arena: spreadsheets | 1434 | 1011 | Claude Fable 5.2 |
| LiveBench research | 94.5% | 72.8% | Claude Fable 5.2 |
| LiveBench browser | 86.9% | 49.4% | Claude Fable 5.2 |
| LiveBench long agentic | 82.9% | 26.6% | Claude Fable 5.2 |
| Finance Agent (Vals AI) | Not measured | 57.9% | Only Qwen3.8 Max (0902) measured |
| Tax Agent Bench (Vals AI) | 32.1% | 49.7% | Qwen3.8 Max (0902) |
| Legal Research Bench (Vals AI) | 46.1% | 47.6% | Qwen3.8 Max (0902) |
| Harvey's Legal Agent Benchmark (Vals AI) | 5.0% | 15.4% | Qwen3.8 Max (0902) |
| Excel Modeling Benchmark (Vals AI) | Not measured | 72.0% | Only Qwen3.8 Max (0902) measured |
| BioMysteryBench (Vals AI) | 83.7% | Not measured | Only Claude Fable 5.2 measured |
| Terminal-Bench-Science (Vals AI) | 55.7% | 12.9% | Claude Fable 5.2 |
| Vals Science Index | 63.7% | Not measured | Only Claude Fable 5.2 measured |
| APEX-Agents | 80.1% | 63.3% | 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 |
| LMArena Search | Not measured | 1260 | Only Qwen3.8 Max (0902) measured |
| τ³-Banking | Not measured | 55.2% | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 93.7% | Only Qwen3.8 Max (0902) measured |
| LiveBench reasoning | 88.8% | 88.2% | Claude Fable 5.2 |
| MysteryMechanism (Vals AI) | 51.8% | 23.9% | Claude Fable 5.2 |
| MMMU Pro (Vals AI) | Not measured | 88.0% | Only Qwen3.8 Max (0902) measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 92.8% | Only Qwen3.8 Max (0902) measured |
| Humanity's Last Exam (Artificial Analysis run) | 74.3% | 43.1% | Claude Fable 5.2 |
| HLE-Diamond (Artificial Analysis run) | 80.2% | 24.0% | Claude Fable 5.2 |
| CritPt v2, hard subset (Artificial Analysis run) | 76.5% | 29.5% | Claude Fable 5.2 |
| GPQA Diamond (Epoch AI run) | 93.9% | 92.7% | Claude Fable 5.2 |
| ARC-AGI | 98.5% | Not measured | Only Claude Fable 5.2 measured |
| ARC-AGI-2 | 93.8% | Not measured | Only Claude Fable 5.2 measured |
| SimpleBench | 94.9% | Not measured | Only Claude Fable 5.2 measured |
| Chess puzzles | 79.0% | 46.0% | Claude Fable 5.2 |
| Mystery game puzzles | 90.0% | 38.0% | Claude Fable 5.2 |
| EBR-bench | 90.5% | Not measured | Only Claude Fable 5.2 measured |
| LMArena Text: hard prompts | Not measured | 1499 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: expert | Not measured | 1510 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: hard prompts in English | Not measured | 1505 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: diagrams | Not measured | 1321 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: homework | Not measured | 1335 | Only Qwen3.8 Max (0902) 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 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.7% | 100.0% | Qwen3.8 Max (0902) |
| FrontierMath, tiers 1 to 3 | 95.1% | 74.7% | Claude Fable 5.2 |
| FrontierMath, tier 4 | 100.0% | 46.3% | Claude Fable 5.2 |
| ProofBench | 100.0% | 58.0% | Claude Fable 5.2 |
| LMArena Text: math | Not measured | 1509 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: mathematical work | Not measured | 1497 | Only Qwen3.8 Max (0902) measured |
| MathArena | 82.8% | 47.1% | 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 index20
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 88.6% | Only Qwen3.8 Max (0902) measured |
| LegalBench (Vals AI) | Not measured | 83.6% | Only Qwen3.8 Max (0902) measured |
| CorpFin (Vals AI) | Not measured | 65.8% | Only Qwen3.8 Max (0902) measured |
| TaxEval (Vals AI) | Not measured | 75.5% | Only Qwen3.8 Max (0902) measured |
| MortgageTax (Vals AI) | Not measured | 64.0% | Only Qwen3.8 Max (0902) measured |
| MedCode (Vals AI) | Not measured | 40.7% | Only Qwen3.8 Max (0902) measured |
| AA-Omniscience | 66.8 | 10.5 | Claude Fable 5.2 |
| SimpleQA Verified | 94.0% | 47.3% | Claude Fable 5.2 |
| LMArena Text: science | Not measured | 1514 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: medicine and healthcare | Not measured | 1514 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: legal and government | Not measured | 1498 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: business and finance | Not measured | 1481 | Only Qwen3.8 Max (0902) measured |
| FACTS Benchmark Suite | Not measured | 60.3% | Only Qwen3.8 Max (0902) 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 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| Design Arena: websites | 1351 | 1269 | Claude Fable 5.2 |
| Design Arena: UI components | 1371 | 1335 | Claude Fable 5.2 |
| Design Arena: game dev | 1396 | 1310 | Claude Fable 5.2 |
| Design Arena: data viz | Not measured | 1281 | Only Qwen3.8 Max (0902) measured |
| Design Arena: 3D | 1517 | 1318 | Claude Fable 5.2 |
| Design Arena: all code categories | 1373 | 1287 | Claude Fable 5.2 |
| Design Arena: ASCII art | Not measured | 1189 | Only Qwen3.8 Max (0902) measured |
| LiveBench design | 85.1% | 76.6% | 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 index70
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| Vals Index | 71.3% | 59.1% | Claude Fable 5.2 |
| LiveBench data analysis | 81.5% | 78.4% | Claude Fable 5.2 |
| Public Benefits Bench (Vals AI) | Not measured | 67.1% | Only Qwen3.8 Max (0902) measured |
| SAGE (Vals AI) | Not measured | 81.8% | Only Qwen3.8 Max (0902) measured |
| MedScribe (Vals AI) | Not measured | 85.0% | Only Qwen3.8 Max (0902) measured |
| Vals Multimodal Index | Not measured | 65.4% | Only Qwen3.8 Max (0902) measured |
| Long context reasoning (AA-LCR) | 83.3% | 80.3% | Claude Fable 5.2 |
| GDPval-AA | 1831 | 1674 | Claude Fable 5.2 |
| DTBench | 99.2% | 92.0% | Claude Fable 5.2 |
| LMCA | 70.6% | 46.2% | Claude Fable 5.2 |
| Furniture assembly | 90.0% | 20.0% | Claude Fable 5.2 |
| LMArena Text | Not measured | 1485 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: instruction following | Not measured | 1483 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: creative writing | Not measured | 1482 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision | Not measured | 1312 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: English | Not measured | 1494 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: non-English | Not measured | 1475 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Chinese | Not measured | 1543 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: German | Not measured | 1475 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Japanese | Not measured | 1463 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Korean | Not measured | 1455 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: French | Not measured | 1504 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Spanish | Not measured | 1494 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Russian | Not measured | 1488 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Polish | Not measured | 1477 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: multi-turn | Not measured | 1492 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: longer queries | Not measured | 1493 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: writing and language | Not measured | 1480 | Only Qwen3.8 Max (0902) measured |
| LMArena Text: entertainment and media | Not measured | 1470 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: English | Not measured | 1310 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: Chinese | Not measured | 1353 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: reading text | Not measured | 1322 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: humor | Not measured | 1309 | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: creative writing | Not measured | 1310 | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.2 | Qwen3.8 Max (0902) | 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
Qwen3.8 Max (0902) costs less
Repository review
50K input + 3K output tokens
Qwen3.8 Max (0902) costs less
Agent loop
200K input + 10K output tokens
Qwen3.8 Max (0902) 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 | Qwen3.8 Max (0902) |
|---|---|---|
| Maker | Anthropic | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | November 9, 2026 | September 3, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $8.00 | $2.00 |
| Output $/Mtok | $40.00 | $6.00 |
| Coding index | 87.8 | 67.3 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | Not computable | $1.32 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.2 better than Qwen3.8 Max (0902) for coding?
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 67.3 for Qwen3.8 Max (0902), though on 4 benchmarks against 5. Pick Qwen3.8 Max (0902) for output tokens 6.7x cheaper ($6.00 vs $40.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
Which is cheaper, Claude Fable 5.2 or Qwen3.8 Max (0902)?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; Qwen3.8 Max (0902) costs $2.00 and $6.00. Cost per solved task is known for Qwen3.8 Max (0902) only.
Which has the bigger context window, Claude Fable 5.2 or Qwen3.8 Max (0902)?
Neither: both take 1M tokens.
How many benchmarks is the Claude Fable 5.2 vs Qwen3.8 Max (0902) comparison based on?
55 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 Qwen3.8 Max (0902)'s on 5. Where only one model has a result, the page says so instead of naming a winner.