# Claude Fable 5 vs Kimi K2.5

> Claude Fable 5 is the stronger model overall, scoring 66.3 to 47.8 on the Noometry Index. Kimi K2.5 costs 22× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Kimi K2.5 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 31.2.
- The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Claude Fable 5 and 11.8% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Claude Fable 5 accepts more context: 1M tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 66.3 | 47.8 |
| Rank | 5 | 50 |
| Context | 1M | 262K |
| Input $/M | $10 | $0.45 |
| Output $/M | $50 | $2.25 |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5: 67.0 (#4)
- Kimi K2.5: 48.7 (#48)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1626 | 1436 |
| SciCode | 61% | 49% |
| WeirdML | 91.9% | 45.6% |
| LMArena Coding | 1519 | 1474 |
| ALE-Bench | 2,041 | 821.65 |
| SWE-bench Verified | — | 73.8% |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
| FrontierSWE | 47% | — |
| MirrorCode | 63.9% | — |

## Agentic & Tool Use

- Claude Fable 5: 54.1 (#2)
- Kimi K2.5: 34.0 (#44)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| Vending-Bench 2 | 5,680 | 1,198 |
| Terminal-Bench | — | 43.2% |
| APEX-Agents | 63.6% | — |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| OSWorld | — | 63.3% |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |

## Reasoning

- Claude Fable 5: 76.8 (#4)
- Kimi K2.5: 31.2 (#74)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 89.2% | 11.8% |
| SimpleBench | 81.9% | 46.8% |
| Kagi LLM Benchmark | 91.4% | 78.5% |
| NYT Connections (extended) | 92.7% | 69.9% |
| ARC-AGI-1 | 98.5% | 65.3% |
| CritPt | 28.6% | 3.1% |
| Chess Puzzles | 41% | 12% |
| EnigmaEval | 39.3% | 3.4% |
| LMArena Hard Prompts | 1508 | 1454 |
| Epoch Capabilities Index | 163.6 | 148.05 |
| Thematic Generalization | — | 69.4% |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| DTBench | 98.4% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |

## Math

- Claude Fable 5: 88.4 (#5)
- Kimi K2.5: 50.3 (#46)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 92.2% |
| LMArena Math | 1519 | 1470 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| MathArena Final-Answer Competitions | — | 62.3% |
| ProofBench | 95% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Claude Fable 5: 62.3 (#22)
- Kimi K2.5: 53.6 (#52)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 85.9% | 87.6% |
| SimpleQA Verified | 70.7% | 34.3% |
| LMArena Expert | 1534 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| Vectara Hallucination Rate | — | 14.2% |

## Multimodal

- Claude Fable 5: 45.6 (#14)
- Kimi K2.5: 40.4 (#37)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1326 | 1269 |
| LMArena Document | 1496 | 1430 |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |

## Multilingual

- Claude Fable 5: 57.6 (#8)
- Kimi K2.5: 54.1 (#50)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1483 | 1433 |
| LMArena Chinese | 1546 | 1495 |
| LMArena French | 1509 | 1454 |
| LMArena German | 1486 | 1441 |
| LMArena Japanese | 1507 | 1422 |
| LMArena Korean | 1493 | 1412 |
| LMArena Russian | 1507 | 1436 |
| LMArena Spanish | 1503 | 1450 |

## Instruction Following

- Claude Fable 5: 78.8 (#7)
- Kimi K2.5: 75.5 (#60)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1503 | 1431 |

## Long Context

- Claude Fable 5: 46.3 (#22)
- Kimi K2.5: 52.1 (#7)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1510 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- Claude Fable 5: 76.1 (#5)
- Kimi K2.5: 65.3 (#51)

| Benchmark | Claude Fable 5 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1491 | 1445 |
| LMArena Creative Writing | 1494 | 1423 |
| EQ-Bench Creative Writing | 1943 | 1579 |
| LMArena Multi-Turn | 1505 | 1444 |
| EQ-Bench 4 | 1340 | — |

## FAQ

### Is Claude Fable 5 better than Kimi K2.5?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 47.8 on the Noometry Index. Kimi K2.5 costs 22× 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 K2.5?

Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Claude Fable 5 lists at $10 and $50.

### Is Claude Fable 5 or Kimi K2.5 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 48.7 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 K2.5 share?

37 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Kimi K2.5 has 51.