# Claude Fable 5.1 vs o3-pro

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 42.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-o3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Claude Fable 5.1 scores higher in 4 categories and o3-pro in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 24.1.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 4.9% for o3-pro.
- Claude Fable 5.1 is cheaper at $10 / $50 per million input/output tokens, against $20 / $80 for o3-pro.
- Claude Fable 5.1 accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Fable 5.1 | o3-pro |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.5 | 42.7 |
| Rank | 2 | 94 |
| Context | 1M | 200K |
| Input $/M | $10 | $20 |
| Output $/M | $50 | $80 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- o3-pro: 55.1 (#22)

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| WeirdML | 92.9% | 58.2% |
| FrontierCode | 50.9% | — |
| Aider Polyglot | — | 84.9% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| LMArena Coding | 1523 | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- o3-pro: —

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- o3-pro: 24.1 (#152)

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| ARC-AGI-2 | 90% | 4.9% |
| ARC-AGI-1 | 97.5% | 59.3% |
| DTBench | 97.6% | 86.9% |
| LMCA | 65.5% | 38.5% |
| Epoch Capabilities Index | 165 | 147.43 |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 90% | — |
| CritPt | 31.1% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| LMArena Hard Prompts | 1526 | — |
| Mystery Game Puzzles | 58% | — |

## Math

- Claude Fable 5.1: 89.5 (#3)
- o3-pro: —

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| LMArena Math | 1519 | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- o3-pro: 29.0 (#234)

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1528 | — |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- o3-pro: —

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- o3-pro: —

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| LMArena Non-English | 1509 | — |
| LMArena Chinese | 1589 | — |
| LMArena French | 1532 | — |
| LMArena German | 1495 | — |
| LMArena Japanese | 1565 | — |
| LMArena Russian | 1525 | — |
| LMArena Spanish | 1503 | — |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- o3-pro: —

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1515 | — |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- o3-pro: 72.1 (#1)

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1524 | — |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- o3-pro: 57.1 (#128)

| Benchmark | Claude Fable 5.1 | o3-pro |
|---|---|---|
| LMArena Text | 1511 | — |
| LMArena Creative Writing | 1507 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 2162 | — |
| LMArena Multi-Turn | 1492 | — |

## FAQ

### Is Claude Fable 5.1 better than o3-pro?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 42.7 on the Noometry Index.

### Which is cheaper, Claude Fable 5.1 or o3-pro?

Claude Fable 5.1 is cheaper. It lists at $10 per million input tokens and $50 per million output tokens; o3-pro lists at $20 and $80.

### Is Claude Fable 5.1 or o3-pro better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 55.1 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 200K.

### How many benchmarks do Claude Fable 5.1 and o3-pro share?

6 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and o3-pro has 12.