# GPT-5.4 mini vs Phi 3 Small 8k Instruct

> GPT-5.4 mini is the stronger model overall, scoring 45.0 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 mini leads 64.0 to 31.1.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 45.0 | 29.3 |
| Rank | 76 | 314 |
| Context | 400K | — |
| Input $/M | $0.75 | — |
| Output $/M | $4.50 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1438 | 1101 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Phi 3 Small 8k Instruct: —

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1100 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| LiveBench Reasoning | — | 15.9% |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 40.8% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1419 | 1151 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| LiveBench Math | — | 17.6% |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1435 | 1067 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Phi 3 Small 8k Instruct: —

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1405 | 1058 |
| LMArena Chinese | 1446 | 1061 |
| LMArena French | 1440 | 1135 |
| LMArena German | 1409 | 1080 |
| LMArena Japanese | 1374 | 966 |
| LMArena Korean | 1368 | 894 |
| LMArena Russian | 1417 | 1111 |
| LMArena Spanish | 1405 | 1111 |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1407 | 1088 |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | GPT-5.4 mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1412 | 1110 |
| LMArena Creative Writing | 1370 | 1083 |
| LMArena Multi-Turn | 1429 | 1068 |
| EQ-Bench Creative Writing | 1665 | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is GPT-5.4 mini better than Phi 3 Small 8k Instruct?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 29.3 on the Noometry Index.

### Is GPT-5.4 mini or Phi 3 Small 8k Instruct better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 27.9 in the Noometry coding category.

### How many benchmarks do GPT-5.4 mini and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Phi 3 Small 8k Instruct has 32.