# Claude 3 Haiku vs Phi 3 Medium 4k Instruct

> Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 25.7 on the Noometry Index.

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

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 3 categories and Phi 3 Medium 4k Instruct in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Medium 4k Instruct leads 30.9 to 9.2.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 25.7 | 32.4 |
| Rank | 333 | 246 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1199 | 1130 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1127 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1188 | 1173 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1148 | 1108 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1178 | 1094 |
| LMArena Chinese | 1155 | 1108 |
| LMArena French | 1194 | 1109 |
| LMArena German | 1174 | 1101 |
| LMArena Japanese | 1102 | 1042 |
| LMArena Korean | 1108 | 954 |
| LMArena Russian | 1204 | 1145 |
| LMArena Spanish | 1165 | 1095 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1174 | 1114 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1191 | 1120 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | Claude 3 Haiku | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1195 | 1138 |
| LMArena Creative Writing | 1157 | 1106 |
| LMArena Multi-Turn | 1190 | 1088 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

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

Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 25.7 on the Noometry Index.

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

Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.3 versus 26.1 in the Noometry coding category.

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

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.
