# Amazon Nova Pro vs Claude Fable 5

> Claude Fable 5 is the stronger model overall, scoring 66.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 14× 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/amazon-nova-pro-vs-claude-fable-5
- Last updated: 2026-10-11
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Claude Fable 5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.5 to 28.5.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Claude Fable 5 accepts more context: 1M tokens versus 300K.

## Snapshot

| | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.0 | 66.8 |
| Rank | 281 | 5 |
| Context | 300K | 1M |
| Input $/M | $0.80 | $10 |
| Output $/M | $3.20 | $50 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Claude Fable 5: 70.6 (#4)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Coding | 1270 | 1519 |
| DeepSWE | — | 69.9% |
| FrontierCode | — | 53.5% |
| LMArena WebDev | — | 1625 |
| FrontierSWE | — | 47% |
| SciCode | — | 61% |
| GSO | — | 78.4% |
| WeirdML | — | 91.9% |
| LiveBench Coding | 38.1% | — |
| MirrorCode | — | 63.9% |
| ALE-Bench | — | 2,041 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Claude Fable 5: 54.0 (#2)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| APEX-Agents | — | 63.6% |
| Berkeley Function Calling Leaderboard | 25% | — |
| Remote Labor Index | — | 16.1% |
| TheAgentCompany | 1.7% | — |
| τ²-bench Banking | — | 39.7% |
| PostTrainBench | — | 41.8% |
| GBAEval | — | 74.5% |
| GDP.pdf | — | 30% |
| LMArena Search | — | 1230 |
| Vending-Bench 2 | — | 5,680 |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Claude Fable 5: 76.8 (#6)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1508 |
| Epoch Capabilities Index | 123.8 | 162.06 |
| ARC-AGI-2 | — | 89.2% |
| SimpleBench | — | 81.9% |
| Kagi LLM Benchmark | — | 91.4% |
| NYT Connections (extended) | — | 92.7% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 28.6% |
| Chess Puzzles | — | 41% |
| EnigmaEval | — | 39.3% |
| EBR-Bench | — | 39.5% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 52% |
| DTBench | — | 98.4% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 61.1% |
| Surface Evolver Bench | — | 95% |
| Bench to the Future 3 | — | 0.13 |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Claude Fable 5: 88.5 (#5)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Math | 1252 | 1519 |
| FrontierMath (Tiers 1-3) | — | 87% |
| FrontierMath Tier 4 | — | 90.2% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 95% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath Erdős | — | 0% |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Claude Fable 5: 62.2 (#25)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Expert | 1211 | 1534 |
| GPQA Diamond | — | 85.9% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 70.7% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Claude Fable 5: 45.3 (#17)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Vision | 980 | 1324 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 35.8% |
| LMArena Document | — | 1496 |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Claude Fable 5: 57.3 (#9)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Non-English | 1234 | 1481 |
| LMArena Chinese | 1244 | 1543 |
| LMArena French | 1271 | 1505 |
| LMArena German | 1243 | 1486 |
| LMArena Japanese | 1200 | 1506 |
| LMArena Korean | 1203 | 1488 |
| LMArena Russian | 1240 | 1504 |
| LMArena Spanish | 1182 | 1498 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Claude Fable 5: 78.6 (#8)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1502 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Claude Fable 5: 46.3 (#23)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1509 |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Claude Fable 5: 75.9 (#5)

| Benchmark | Amazon Nova Pro | Claude Fable 5 |
|---|---|---|
| LMArena Text | 1259 | 1491 |
| LMArena Creative Writing | 1212 | 1494 |
| LMArena Multi-Turn | 1246 | 1504 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1943 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1340 |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Claude Fable 5?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 14× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Pro or Claude Fable 5?

Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Claude Fable 5 lists at $10 and $50.

### Is Amazon Nova Pro or Claude Fable 5 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 300K.

### How many benchmarks do Amazon Nova Pro and Claude Fable 5 share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude Fable 5 has 62.