# Claude Fable 5.1 vs Phi 3 Mini 4k Instruct

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 24.5.
- The biggest single-benchmark swing is Chess Puzzles: 47% for Claude Fable 5.1 and 0% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 68.5 | 27.4 |
| Rank | 2 | 324 |
| Context | 1M | — |
| Input $/M | $10 | — |
| Output $/M | $50 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- Phi 3 Mini 4k Instruct: 26.1 (#319)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1523 | 1093 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| WeirdML | 92.9% | — |
| LiveBench Coding | — | 15.5% |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| 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)
- Phi 3 Mini 4k Instruct: 13.6 (#326)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 47% | 0% |
| LMArena Hard Prompts | 1526 | 1072 |
| ARC-AGI-2 | 90% | — |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| EBR-Bench | 57.1% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 65.5% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 165 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- Claude Fable 5.1: 89.5 (#3)
- Phi 3 Mini 4k Instruct: 24.5 (#258)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1519 | 1111 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| LiveBench Math | — | 15.7% |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- Phi 3 Mini 4k Instruct: 27.9 (#241)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1528 | 1045 |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- Phi 3 Mini 4k Instruct: 26.5 (#275)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1509 | 1021 |
| LMArena Chinese | 1589 | 1021 |
| LMArena French | 1532 | 1075 |
| LMArena German | 1495 | 1044 |
| LMArena Japanese | 1565 | 935 |
| LMArena Russian | 1525 | 1022 |
| LMArena Spanish | 1503 | 1084 |
| LMArena Korean | — | 905 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- Phi 3 Mini 4k Instruct: 48.0 (#298)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1515 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- Phi 3 Mini 4k Instruct: 31.7 (#271)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1524 | 1044 |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- Phi 3 Mini 4k Instruct: 27.7 (#295)

| Benchmark | Claude Fable 5.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1511 | 1073 |
| LMArena Creative Writing | 1507 | 1037 |
| LMArena Multi-Turn | 1492 | 1018 |
| EQ-Bench Creative Writing | 2162 | — |
| LiveBench Language | — | 9.2% |

## FAQ

### Is Claude Fable 5.1 better than Phi 3 Mini 4k Instruct?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 27.4 on the Noometry Index.

### Is Claude Fable 5.1 or Phi 3 Mini 4k Instruct better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude Fable 5.1 and Phi 3 Mini 4k Instruct share?

17 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.