# Claude Haiku 4.5 vs Phi 3 Medium 4k Instruct

> Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-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 Haiku 4.5 scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Haiku 4.5 leads 58.1 to 34.3.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 39.3 | 32.4 |
| Rank | 155 | 246 |
| Context | 200K | — |
| Input $/M | $1 | — |
| Output $/M | $5 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 4.5: 43.9 (#71)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1454 | 1130 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.5 (#50)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#310)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1127 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.42 | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 43.0 (#69)
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1395 | 1173 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.6 (#146)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1443 | 1108 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 27.0 (#111)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 50.1 (#124)
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1376 | 1094 |
| LMArena Chinese | 1415 | 1108 |
| LMArena French | 1408 | 1109 |
| LMArena German | 1377 | 1101 |
| LMArena Japanese | 1339 | 1042 |
| LMArena Korean | 1346 | 954 |
| LMArena Russian | 1380 | 1145 |
| LMArena Spanish | 1420 | 1095 |

## Instruction Following

- Claude Haiku 4.5: 71.6 (#144)
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1414 | 1114 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#86)
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1427 | 1120 |

## Writing & Preference

- Claude Haiku 4.5: 58.1 (#119)
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | Claude Haiku 4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1396 | 1138 |
| LMArena Creative Writing | 1371 | 1106 |
| LMArena Multi-Turn | 1409 | 1088 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Phi 3 Medium 4k Instruct?

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 32.4 on the Noometry Index.

### Is Claude Haiku 4.5 or Phi 3 Medium 4k Instruct better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 32.3 in the Noometry coding category.

### How many benchmarks do Claude Haiku 4.5 and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.