# Claude Fable 5.1 vs o4-mini

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 41.6 on the Noometry Index. o4-mini costs 10× 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-o4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and o4-mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 24.6.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 6.1% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 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 | o4-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.5 | 41.6 |
| Rank | 2 | 119 |
| Context | 1M | 200K |
| Input $/M | $10 | $1.10 |
| Output $/M | $50 | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- o4-mini: 41.6 (#110)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| WeirdML | 92.9% | 52.6% |
| LMArena Coding | 1523 | 1369 |
| ALE-Bench | 2,143 | 826.17 |
| FrontierCode | 50.9% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | — | 3.6% |
| MirrorCode | 73.3% | — |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- o4-mini: 32.3 (#57)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- o4-mini: 24.6 (#143)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 90% | 6.1% |
| ARC-AGI-1 | 97.5% | 58.7% |
| CritPt | 31.1% | 0.6% |
| Chess Puzzles | 47% | 26% |
| LMArena Hard Prompts | 1526 | 1351 |
| Mystery Game Puzzles | 58% | 5% |
| DTBench | 97.6% | 77.6% |
| LMCA | 65.5% | 26.5% |
| Epoch Capabilities Index | 165 | 145.63 |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 90% | — |
| EnigmaEval | — | 9.2% |
| EBR-Bench | 57.1% | — |
| ForecastBench | — | 61.8 |

## Math

- Claude Fable 5.1: 89.5 (#3)
- o4-mini: 40.2 (#79)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 36.1% |
| FrontierMath Tier 4 | 87.8% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 81.7% |
| LMArena Math | 1519 | 1390 |
| ProofBench | 100% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- o4-mini: 43.5 (#83)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| Humanity's Last Exam | 46.5% | 18.1% |
| SimpleQA Verified | 70.8% | 19.6% |
| LMArena Expert | 1528 | 1344 |
| GPQA Diamond | — | 79.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- o4-mini: 39.5 (#46)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| LMArena Vision | 1319 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- o4-mini: 47.2 (#149)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| LMArena Non-English | 1509 | 1336 |
| LMArena Chinese | 1589 | 1355 |
| LMArena French | 1532 | 1362 |
| LMArena German | 1495 | 1336 |
| LMArena Japanese | 1565 | 1308 |
| LMArena Russian | 1525 | 1334 |
| LMArena Spanish | 1503 | 1346 |
| LMArena Korean | — | 1313 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- o4-mini: 75.4 (#63)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1515 | 1321 |
| IFEval | — | 92.8% |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- o4-mini: 45.5 (#31)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1524 | 1315 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- o4-mini: 54.2 (#148)

| Benchmark | Claude Fable 5.1 | o4-mini |
|---|---|---|
| LMArena Text | 1511 | 1353 |
| LMArena Creative Writing | 1507 | 1294 |
| LMArena Multi-Turn | 1492 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 2162 | — |
| WildBench | — | 85.4% |

## FAQ

### Is Claude Fable 5.1 better than o4-mini?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 41.6 on the Noometry Index. o4-mini costs 10× 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 o4-mini?

o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or o4-mini better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 41.6 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 o4-mini share?

32 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and o4-mini has 60.