# Claude 3 Haiku vs Phi 3 Small 8k Instruct

> Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Phi 3 Small 8k Instruct in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Small 8k Instruct leads 27.6 to 9.8.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 25.9 | 29.3 |
| Rank | 340 | 314 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1199 | 1101 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| LiveBench Coding | — | 20.3% |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1100 |
| WinoGrande | 74.2% | 81.5% |
| Kagi LLM Benchmark | 34.2% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 50.1% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 8.8% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1188 | 1151 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1148 | 1067 |
| MMLU | 73.8% | 75.7% |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Phi 3 Small 8k Instruct: —

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1178 | 1058 |
| LMArena Chinese | 1155 | 1061 |
| LMArena French | 1195 | 1135 |
| LMArena German | 1174 | 1080 |
| LMArena Japanese | 1102 | 966 |
| LMArena Korean | 1109 | 894 |
| LMArena Russian | 1204 | 1111 |
| LMArena Spanish | 1166 | 1111 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1173 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1190 | 1088 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | Claude 3 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1195 | 1110 |
| LMArena Creative Writing | 1157 | 1083 |
| LMArena Multi-Turn | 1190 | 1068 |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is Claude 3 Haiku better than Phi 3 Small 8k Instruct?

Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Phi 3 Small 8k Instruct better for coding?

Phi 3 Small 8k Instruct scores higher on coding benchmarks: 27.9 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Phi 3 Small 8k Instruct share?

19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Phi 3 Small 8k Instruct has 32.