# Claude Haiku 5.5 vs Phi 3 Mini 4k Instruct

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 26.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 49.5 | 27.9 |
| Rank | 52 | 328 |
| Context | 1M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.50 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena WebDev | 1587 | — |
| LiveBench Coding | — | 15.5% |
| LMArena Coding | — | 1093 |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| NYT Connections (extended) | 65.7% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LMArena Hard Prompts | — | 1072 |
| Mystery Game Puzzles | 30% | — |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| LiveBench Math | — | 15.7% |
| LMArena Math | — | 1111 |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| GPQA Diamond | 89.6% | — |
| SimpleQA Verified | 23.8% | — |
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |

## Instruction Following

- Claude Haiku 5.5: —
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 39.1% |
| LMArena Instruction Following | — | 1053 |

## Long Context

- Claude Haiku 5.5: —
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |

## Writing & Preference

- Claude Haiku 5.5: —
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Claude Haiku 5.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | — | 1073 |
| LMArena Creative Writing | — | 1037 |
| LMArena Multi-Turn | — | 1018 |
| LiveBench Language | — | 9.2% |

## FAQ

### Is Claude Haiku 5.5 better than Phi 3 Mini 4k Instruct?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 27.9 on the Noometry Index.

### Is Claude Haiku 5.5 or Phi 3 Mini 4k Instruct better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 26.6 in the Noometry coding category.

### How many benchmarks do Claude Haiku 5.5 and Phi 3 Mini 4k Instruct share?

0 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.