Model comparison
Claude Fable 5 vs Kimi K2.6
Claude Fable 5 is the stronger model overall, scoring 66.3 to 47.5 on the Noometry Index. Kimi K2.6 costs 12× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude Fable 5 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 leads 76.8 to 39.6.
- The biggest single-benchmark swing is ProofBench: 95% for Claude Fable 5 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.
- Claude Fable 5 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 | Kimi K2.6 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 66.3 | 47.5 |
| Released | 2026-06-07 | 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 | 61 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 67.0 (#4), Kimi K2.6: 50.5 (#41)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1626 | 1509 |
| SciCode | 61% | 53.5% |
| WeirdML | 91.9% | 55.9% |
| LMArena Coding | 1519 | 1488 |
| ALE-Bench | 2,041 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| FrontierSWE | 47% | — |
| MirrorCode | 63.9% | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.1 (#2), Kimi K2.6: 21.8 (#128)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| GBAEval | 74.5% | 0.9% |
| GDP.pdf | 30% | 12% |
| Vending-Bench 2 | 5,680 | 6,205 |
| APEX-Agents | 63.6% | — |
| OSWorld 2.0 | — | 4.6% |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| ExploitBench | — | 18.4% |
| LMArena Search | 1230 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#4), Kimi K2.6: 39.6 (#51)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 92.7% | 87.2% |
| CritPt | 28.6% | 8% |
| Chess Puzzles | 41% | 26% |
| EBR-Bench | 39.5% | 2.4% |
| LMArena Hard Prompts | 1508 | 1470 |
| Mystery Game Puzzles | 52% | 18% |
| DTBench | 98.4% | 90.9% |
| LMCA | 61.1% | 37.3% |
| Epoch Capabilities Index | 163.6 | 151.03 |
| ARC-AGI-2 | 89.2% | — |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| ARC-AGI-1 | 98.5% | — |
| EnigmaEval | 39.3% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.4 (#5), Kimi K2.6: 56.8 (#34)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 57.2% |
| FrontierMath Tier 4 | 90.2% | 25.6% |
| OTIS Mock AIME 2024-2025 | 100% | 96.1% |
| ProofBench | 95% | 16% |
| LMArena Math | 1519 | 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 leads
Claude Fable 5: 62.3 (#22), Kimi K2.6: 53.9 (#48)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 85.9% | 90.8% |
| SimpleQA Verified | 70.7% | 34.9% |
| LMArena Expert | 1534 | 1491 |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal Claude Fable 5 leads
Claude Fable 5: 45.6 (#14), Kimi K2.6: 31.8 (#95)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1326 | 1282 |
| Blueprint-Bench 2 | 38.6% | 3.9% |
| Furniture Assembly | 35.8% | 21.7% |
| LMArena Document | 1496 | 1451 |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.6 (#8), Kimi K2.6: 55.1 (#35)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1483 | 1446 |
| LMArena Chinese | 1546 | 1521 |
| LMArena French | 1509 | 1471 |
| LMArena German | 1486 | 1449 |
| LMArena Japanese | 1507 | 1442 |
| LMArena Korean | 1493 | 1428 |
| LMArena Russian | 1507 | 1446 |
| LMArena Spanish | 1503 | 1463 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.8 (#7), Kimi K2.6: 76.5 (#40)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1503 | 1451 |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#22), Kimi K2.6: 44.9 (#50)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1510 | 1468 |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 76.1 (#5), Kimi K2.6: 68.7 (#25)
| Benchmark | Claude Fable 5 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1491 | 1455 |
| LMArena Creative Writing | 1494 | 1434 |
| EQ-Bench Creative Writing | 1943 | 1725 |
| EQ-Bench 4 | 1340 | 1202 |
| LMArena Multi-Turn | 1505 | 1453 |
Frequently asked questions
Is Claude Fable 5 better than Kimi K2.6?
Claude Fable 5 is the stronger model overall, scoring 66.3 to 47.5 on the Noometry Index. Kimi K2.6 costs 12× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5 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 lists at $10 and $50.
Is Claude Fable 5 or Kimi K2.6 better for coding?
Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 50.5 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5 does, with 1M tokens against 262K.
How many benchmarks do Claude Fable 5 and Kimi K2.6 share?
44 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Kimi K2.6 has 51.