# o4-mini vs Phi 3 Mini 4k Instruct

> o4-mini is the stronger model overall, scoring 41.6 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o4-mini-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. o4-mini 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 instruction following, where o4-mini leads 75.4 to 48.0.
- The biggest single-benchmark swing is Chess Puzzles: 26% for o4-mini and 0% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 41.6 | 27.4 |
| Rank | 119 | 324 |
| Context | 200K | — |
| Input $/M | $1.10 | — |
| Output $/M | $4.40 | — |
| Weights | Proprietary | Open |

## Coding

- o4-mini: 41.6 (#110)
- Phi 3 Mini 4k Instruct: 26.1 (#319)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1369 | 1093 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| LiveBench Coding | — | 15.5% |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

- o4-mini: 32.3 (#57)
- Phi 3 Mini 4k Instruct: —

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |

## Reasoning

- o4-mini: 24.6 (#143)
- Phi 3 Mini 4k Instruct: 13.6 (#326)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 26% | 0% |
| LMArena Hard Prompts | 1351 | 1072 |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 58.7% | — |
| CritPt | 0.6% | — |
| EnigmaEval | 9.2% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 5% | — |
| DTBench | 77.6% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 26.5% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 145.63 | — |
| ForecastBench | 61.8 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- o4-mini: 40.2 (#79)
- Phi 3 Mini 4k Instruct: 24.5 (#258)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1390 | 1111 |
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| Omni-MATH | 72% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |

## Knowledge

- o4-mini: 43.5 (#83)
- Phi 3 Mini 4k Instruct: 27.9 (#241)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1344 | 1045 |
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multimodal

- o4-mini: 39.5 (#46)
- Phi 3 Mini 4k Instruct: —

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1194 | — |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |

## Multilingual

- o4-mini: 47.2 (#149)
- Phi 3 Mini 4k Instruct: 26.5 (#275)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1336 | 1021 |
| LMArena Chinese | 1355 | 1021 |
| LMArena French | 1362 | 1075 |
| LMArena German | 1336 | 1044 |
| LMArena Japanese | 1308 | 935 |
| LMArena Korean | 1313 | 905 |
| LMArena Russian | 1334 | 1022 |
| LMArena Spanish | 1346 | 1084 |

## Instruction Following

- o4-mini: 75.4 (#63)
- Phi 3 Mini 4k Instruct: 48.0 (#298)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1321 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 92.8% | — |

## Long Context

- o4-mini: 45.5 (#31)
- Phi 3 Mini 4k Instruct: 31.7 (#271)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1315 | 1044 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- o4-mini: 54.2 (#148)
- Phi 3 Mini 4k Instruct: 27.7 (#295)

| Benchmark | o4-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1353 | 1073 |
| LMArena Creative Writing | 1294 | 1037 |
| LMArena Multi-Turn | 1350 | 1018 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 9.2% |

## FAQ

### Is o4-mini better than Phi 3 Mini 4k Instruct?

o4-mini is the stronger model overall, scoring 41.6 to 27.4 on the Noometry Index.

### Is o4-mini or Phi 3 Mini 4k Instruct better for coding?

o4-mini scores higher on coding benchmarks: 41.6 versus 26.1 in the Noometry coding category.

### How many benchmarks do o4-mini and Phi 3 Mini 4k Instruct share?

18 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.