# Claude Fable 5.1 vs o3

> Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 47.5 on the Noometry Index. o3 costs 5.7× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-o3
- Last updated: 2026-10-11
- Shared benchmarks: 34

## Summary

- They share 34 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and o3 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 32.0.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 6.5% for o3.
- o3 is cheaper at $2 / $8 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Fable 5.1 | o3 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 69.0 | 47.5 |
| Rank | 2 | 61 |
| Context | 1M | 200K |
| Input $/M | $10 | $2 |
| Output $/M | $50 | $8 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 74.7 (#1)
- o3: 46.8 (#64)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| GSO | 88.2% | 8.8% |
| WeirdML | 92.9% | 52.4% |
| LMArena Coding | 1528 | 1408 |
| ALE-Bench | 2,143 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| FrontierCode | 50.9% | — |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| MirrorCode | 73.3% | — |
| CadEval | — | 74% |

## Agentic & Tool Use

- Claude Fable 5.1: 50.7 (#5)
- o3: 34.5 (#44)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| Remote Labor Index | 17.9% | — |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| GDP.pdf | 29.6% | — |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#7)
- o3: 32.0 (#78)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| ARC-AGI-2 | 90% | 6.5% |
| ARC-AGI-1 | 97.5% | 60.8% |
| CritPt | 31.1% | 1.4% |
| Chess Puzzles | 47% | 38% |
| LMArena Hard Prompts | 1526 | 1402 |
| Mystery Game Puzzles | 58% | 29% |
| DTBench | 97.6% | 84.8% |
| LMCA | 65.5% | 39.7% |
| Epoch Capabilities Index | 164.7 | 146.86 |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 90% | — |
| EnigmaEval | — | 13.1% |
| EBR-Bench | 57.1% | — |
| ForecastBench | — | 62.5 |

## Math

- Claude Fable 5.1: 89.6 (#4)
- o3: 50.2 (#58)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 33.3% |
| OTIS Mock AIME 2024-2025 | 100% | 84.4% |
| LMArena Math | 1525 | 1426 |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude Fable 5.1: 69.6 (#6)
- o3: 54.6 (#52)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| Humanity's Last Exam | 46.5% | 20.3% |
| SimpleQA Verified | 70.8% | 49.4% |
| LMArena Expert | 1535 | 1402 |
| GPQA Diamond | — | 81.8% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |

## Multimodal

- Claude Fable 5.1: 53.9 (#4)
- o3: 41.4 (#36)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| LMArena Vision | 1318 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.1 (#3)
- o3: 51.7 (#105)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| LMArena Non-English | 1507 | 1401 |
| LMArena Chinese | 1586 | 1437 |
| LMArena French | 1525 | 1430 |
| LMArena German | 1500 | 1420 |
| LMArena Japanese | 1543 | 1403 |
| LMArena Korean | 1534 | 1370 |
| LMArena Russian | 1521 | 1406 |
| LMArena Spanish | 1516 | 1395 |

## Instruction Following

- Claude Fable 5.1: 79.2 (#6)
- o3: 72.8 (#127)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1368 |
| IFEval | — | 86.9% |

## Long Context

- Claude Fable 5.1: 46.7 (#20)
- o3: 53.3 (#6)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| LMArena Longer Query | 1522 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- Claude Fable 5.1: 79.2 (#2)
- o3: 63.5 (#64)

| Benchmark | Claude Fable 5.1 | o3 |
|---|---|---|
| LMArena Text | 1510 | 1410 |
| LMArena Creative Writing | 1507 | 1359 |
| EQ-Bench Creative Writing | 2162 | 1676 |
| LMArena Multi-Turn | 1492 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |

## FAQ

### Is Claude Fable 5.1 better than o3?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 47.5 on the Noometry Index. o3 costs 5.7× 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 o3?

o3 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

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

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 46.8 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 share?

34 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and o3 has 63.