Claude Fable 5.2 vs Kimi K3.1 Pro
Claude Fable 5.2 leads Kimi K3.1 Pro on coding, 87.8 to 79.0 on the Vibe Coding Index, and Kimi K3.1 Pro costs 4.0x less per output token ($10.00 vs $40.00 per million). Updated November 14, 2026; 48 benchmarks have a result for both.
Claude Fable 5.2 or Kimi K3.1 Pro: which to pick
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 79.0 for Kimi K3.1 Pro.
Pick Kimi K3.1 Pro for output tokens 4.0x cheaper ($10.00 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).
- Shared results
- 48
- Claude Fable 5.2 only
- 20
- Kimi K3.1 Pro only
- 31
- 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 79.0.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Fable 5.2
Claude Fable 5.2 leads, 64.6 against 46.5.
Same board, both measured
Web design
Design Arena: websites
Claude Fable 5.2
Claude Fable 5.2 leads, 1351 against 1321.
Same board, both measured
General
Vals Index
Claude Fable 5.2
Claude Fable 5.2 leads, 71.3% against 62.5%.
Same board, both measured
Long documents
Listed context window
Kimi K3.1 Pro
Kimi K3.1 Pro takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K3.1 Pro
Claude Fable 5.2 $0.028, Kimi K3.1 Pro $0.0070 per turn.
List prices
At a glance
- Coding index
- Claude Fable 5.2 87.8 from 4 benchmarks, Kimi K3.1 Pro 79.0 from 4 benchmarks.
- Widest category
- Reasoning, 23.9 points apart on average over 5 shared benchmarks.
- Widest single gap
- LiveBench long agentic: Claude Fable 5.2 82.9% against Kimi K3.1 Pro 38.7%, 44.2 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.2 $40.00 against Kimi K3.1 Pro $10.00 per million output tokens, 4.0x apart.
- Context window
- Claude Fable 5.2 takes 1M tokens, Kimi K3.1 Pro 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 | Kimi K3.1 Pro | Ties |
|---|---|---|---|---|
| Coding | 10 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 12 | 1 | ||
| Reasoning | 4 | 1 | ||
| Math | 2 | 0 | ||
| Knowledge | 2 | 1 | ||
| Web design | 4 | 2 | ||
| General | 4 | 2 | ||
| All shared boards | 40 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index101
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| LiveBench coding | 79.2% | 67.8% | Claude Fable 5.2 |
| LMArena WebDev | 1838 | 1687 | Claude Fable 5.2 |
| Terminal-Bench 4 (Vals AI) | 65.2% | 63.6% | Claude Fable 5.2 |
| Vibe Code Bench (Vals AI) | 93.8% | 84.9% | Claude Fable 5.2 |
| ProgramBench (Vals AI) | 19.0% | Not measured | Only Claude Fable 5.2 measured |
| IOI (Vals AI) | Not measured | 81.9% | Only Kimi K3.1 Pro measured |
| SWE-bench Multimodal (Vals AI) | 62.3% | Not measured | Only Claude Fable 5.2 measured |
| SciCode | 67.7% | 60.8% | Claude Fable 5.2 |
| Terminal-Bench 4.0 (Artificial Analysis run) | 61.6% | 67.2% | Kimi K3.1 Pro |
| FrontierCode 2.0 | 49.1% | 25.5% | Claude Fable 5.2 |
| FrontierSWE | 69.9% | Not measured | Only Claude Fable 5.2 measured |
| ALE-Bench | 2509.8 | 1932.8 | Claude Fable 5.2 |
| LMArena Text: coding | Not measured | 1480 | Only Kimi K3.1 Pro measured |
| LMArena Text: software and IT | Not measured | 1482 | Only Kimi K3.1 Pro measured |
| LMArena WebDev: React | 1915 | 1699 | Claude Fable 5.2 |
| LMArena WebDev: HTML | 1738 | 1689 | Claude Fable 5.2 |
| GameBench 2 | 99.1 | 84.0 | Claude Fable 5.2 |
| Terminal-Bench 4.0 | Not measured | 60.9% | Only Kimi K3.1 Pro measured |
| CursorBench 4.0 | 60.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 64.6 | 46.5 | Claude Fable 5.2 |
| Epoch Capabilities Index | 173.4 | 161.4 | Claude Fable 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index121
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1312 | Only Kimi K3.1 Pro measured |
| Design Arena: agents building full-stack apps | 1402 | 1321 | Claude Fable 5.2 |
| Design Arena: agents building mobile apps | 1325 | 1268 | Claude Fable 5.2 |
| Design Arena: agents building Android apps | Not measured | 1147 | Only Kimi K3.1 Pro measured |
| Design Arena: PowerPoint slides | Not measured | 1278 | Only Kimi K3.1 Pro measured |
| Design Arena: spreadsheets | 1434 | 1326 | Claude Fable 5.2 |
| LiveBench research | 94.5% | 82.1% | Claude Fable 5.2 |
| LiveBench browser | 86.9% | 75.9% | Claude Fable 5.2 |
| LiveBench long agentic | 82.9% | 38.7% | Claude Fable 5.2 |
| SREBench (Vals AI) | Not measured | 27.1% | Only Kimi K3.1 Pro measured |
| Tax Agent Bench (Vals AI) | 32.1% | 24.9% | Claude Fable 5.2 |
| Legal Research Bench (Vals AI) | 46.1% | 37.5% | Claude Fable 5.2 |
| Harvey's Legal Agent Benchmark (Vals AI) | 5.0% | 11.7% | Kimi K3.1 Pro |
| BioMysteryBench (Vals AI) | 83.7% | 75.6% | Claude Fable 5.2 |
| Terminal-Bench-Science (Vals AI) | 55.7% | 31.4% | Claude Fable 5.2 |
| Vals Science Index | 63.7% | 44.4% | Claude Fable 5.2 |
| APEX-Agents | 80.1% | 65.5% | 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 |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.8% | 91.1% | Kimi K3.1 Pro |
| MysteryMechanism (Vals AI) | 51.8% | 26.1% | Claude Fable 5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 74.3% | 52.5% | Claude Fable 5.2 |
| HLE-Diamond (Artificial Analysis run) | 80.2% | 37.3% | Claude Fable 5.2 |
| CritPt v2, hard subset (Artificial Analysis run) | 76.5% | 49.5% | Claude Fable 5.2 |
| GPQA Diamond (Epoch AI run) | 93.9% | Not measured | Only Claude Fable 5.2 measured |
| 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% | Not measured | Only Claude Fable 5.2 measured |
| 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 | 1471 | Only Kimi K3.1 Pro measured |
| LMArena Text: expert | Not measured | 1489 | Only Kimi K3.1 Pro measured |
| LMArena Text: hard prompts in English | Not measured | 1486 | Only Kimi K3.1 Pro 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 index20
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.7% | Not measured | Only Claude Fable 5.2 measured |
| 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% | 91.0% | Claude Fable 5.2 |
| LMArena Text: mathematical work | Not measured | 1451 | Only Kimi K3.1 Pro measured |
| MathArena | 82.8% | 54.3% | Claude Fable 5.2 |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| AA-Omniscience | 66.8 | 29.9 | Claude Fable 5.2 |
| SimpleQA Verified | 94.0% | Not measured | Only Claude Fable 5.2 measured |
| LMArena Text: science | Not measured | 1464 | Only Kimi K3.1 Pro measured |
| LMArena Text: medicine and healthcare | Not measured | 1413 | Only Kimi K3.1 Pro measured |
| LMArena Text: legal and government | Not measured | 1495 | Only Kimi K3.1 Pro measured |
| LMArena Text: business and finance | Not measured | 1472 | Only Kimi K3.1 Pro measured |
| PRBench Finance | 47.1% | 47.5% | Kimi K3.1 Pro |
| PRBench Legal | 49.0% | 47.9% | Claude Fable 5.2 |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1351 | 1321 | Claude Fable 5.2 |
| Design Arena: UI components | 1371 | 1389 | Kimi K3.1 Pro |
| Design Arena: game dev | 1396 | 1404 | Kimi K3.1 Pro |
| Design Arena: data viz | Not measured | 1298 | Only Kimi K3.1 Pro measured |
| Design Arena: 3D | 1517 | 1442 | Claude Fable 5.2 |
| Design Arena: all code categories | 1373 | 1350 | Claude Fable 5.2 |
| Design Arena: SVG | Not measured | 1329 | Only Kimi K3.1 Pro measured |
| Design Arena: ASCII art | Not measured | 1301 | Only Kimi K3.1 Pro measured |
| LiveBench design | 85.1% | 73.7% | Claude Fable 5.2 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Vals Index | 71.3% | 62.5% | Claude Fable 5.2 |
| LiveBench data analysis | 81.5% | 79.1% | Claude Fable 5.2 |
| Long context reasoning (AA-LCR) | 83.3% | 86.3% | Kimi K3.1 Pro |
| GDPval-AA | 1831 | 1861 | Kimi K3.1 Pro |
| DTBench | 99.2% | 93.3% | Claude Fable 5.2 |
| LMCA | 70.6% | 57.6% | Claude Fable 5.2 |
| Furniture assembly | 90.0% | Not measured | Only Claude Fable 5.2 measured |
| LMArena Text | Not measured | 1459 | Only Kimi K3.1 Pro measured |
| LMArena Text: instruction following | Not measured | 1472 | Only Kimi K3.1 Pro measured |
| LMArena Text: creative writing | Not measured | 1439 | Only Kimi K3.1 Pro measured |
| LMArena Text: English | Not measured | 1466 | Only Kimi K3.1 Pro measured |
| LMArena Text: non-English | Not measured | 1450 | Only Kimi K3.1 Pro measured |
| LMArena Text: Chinese | Not measured | 1516 | Only Kimi K3.1 Pro measured |
| LMArena Text: Spanish | Not measured | 1503 | Only Kimi K3.1 Pro measured |
| LMArena Text: Russian | Not measured | 1452 | Only Kimi K3.1 Pro measured |
| LMArena Text: multi-turn | Not measured | 1449 | Only Kimi K3.1 Pro measured |
| LMArena Text: longer queries | Not measured | 1468 | Only Kimi K3.1 Pro measured |
| LMArena Text: writing and language | Not measured | 1458 | Only Kimi K3.1 Pro measured |
| LMArena Text: entertainment and media | Not measured | 1460 | Only Kimi K3.1 Pro measured |
| Neither model has a result on the other 30 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.2 | Kimi K3.1 Pro | 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
Kimi K3.1 Pro costs less
Repository review
50K input + 3K output tokens
Kimi K3.1 Pro costs less
Agent loop
200K input + 10K output tokens
Kimi K3.1 Pro 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 | MoonshotAI Kimi K3.1 Pro |
|---|---|---|
| Maker | Anthropic | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | November 9, 2026 | October 23, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $8.00 | $2.00 |
| Output $/Mtok | $40.00 | $10.00 |
| Coding index | 87.8 | 79.0 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.2 better than Kimi K3.1 Pro for coding?
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 79.0 for Kimi K3.1 Pro. Pick Kimi K3.1 Pro 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 Kimi K3.1 Pro?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; Kimi K3.1 Pro 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 Kimi K3.1 Pro?
Kimi K3.1 Pro, with 1.05M tokens against 1M.
How many benchmarks is the Claude Fable 5.2 vs Kimi K3.1 Pro comparison based on?
48 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 Kimi K3.1 Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.