Model comparison
Claude Fable 5.1 vs Kimi K2.6
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 47.7 on the Noometry Index. Kimi K2.6 costs 12× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and Kimi K2.6 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 40.5.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 16% for Kimi K2.6.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | Kimi K2.6 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 69.0 | 47.7 |
| Released | 2026-09-01 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $10 | $0.95 |
| Output $ / M tokens | $50 | $4 |
| Results tracked | 52 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Kimi K2.6: 50.7 (#43)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1744 | 1509 |
| SciCode | 63.1% | 53.5% |
| WeirdML | 92.9% | 55.9% |
| LMArena Coding | 1528 | 1488 |
| ALE-Bench | 2,143 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), Kimi K2.6: 21.9 (#137)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| GDP.pdf | 29.6% | 12% |
| Vending-Bench 2 | 5,422 | 6,205 |
| APEX-Agents | 68.6% | — |
| OSWorld 2.0 | — | 4.6% |
| Remote Labor Index | 17.9% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Kimi K2.6: 40.5 (#55)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 90% | 87.2% |
| CritPt | 31.1% | 8% |
| Chess Puzzles | 47% | 26% |
| EBR-Bench | 57.1% | 2.4% |
| LMArena Hard Prompts | 1526 | 1470 |
| Mystery Game Puzzles | 58% | 18% |
| DTBench | 97.6% | 90.9% |
| LMCA | 65.5% | 37.3% |
| Epoch Capabilities Index | 164.7 | 151.05 |
| ARC-AGI-2 | 90% | — |
| ARC-AGI-1 | 97.5% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Kimi K2.6: 57.0 (#41)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 57.2% |
| FrontierMath Tier 4 | 87.8% | 25.6% |
| OTIS Mock AIME 2024-2025 | 100% | 96.1% |
| ProofBench | 100% | 16% |
| LMArena Math | 1525 | 1475 |
| MathArena Final-Answer Competitions | — | 72.9% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Kimi K2.6: 54.0 (#54)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| SimpleQA Verified | 70.8% | 34.9% |
| LMArena Expert | 1535 | 1491 |
| GPQA Diamond | — | 90.8% |
| Humanity's Last Exam | 46.5% | — |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), Kimi K2.6: 31.6 (#103)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1318 | 1283 |
| Blueprint-Bench 2 | 41.9% | 3.9% |
| Furniture Assembly | 70% | 21.7% |
| LMArena Document | 1513 | 1451 |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Kimi K2.6: 54.9 (#37)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1507 | 1446 |
| LMArena Chinese | 1586 | 1521 |
| LMArena French | 1525 | 1471 |
| LMArena German | 1500 | 1450 |
| LMArena Japanese | 1543 | 1443 |
| LMArena Korean | 1534 | 1427 |
| LMArena Russian | 1521 | 1446 |
| LMArena Spanish | 1516 | 1464 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Kimi K2.6: 76.3 (#43)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1451 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Kimi K2.6: 44.9 (#52)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1522 | 1468 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Kimi K2.6: 68.5 (#26)
| Benchmark | Claude Fable 5.1 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1510 | 1455 |
| LMArena Creative Writing | 1507 | 1434 |
| EQ-Bench Creative Writing | 2162 | 1725 |
| LMArena Multi-Turn | 1492 | 1453 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Claude Fable 5.1 better than Kimi K2.6?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 47.7 on the Noometry Index. Kimi K2.6 costs 12× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or Kimi K2.6?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or Kimi K2.6 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 50.7 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5.1 does, with 1M tokens against 262K.
How many benchmarks do Claude Fable 5.1 and Kimi K2.6 share?
41 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Kimi K2.6 has 51.