# gpt-oss-120b vs phi-3-medium 14B

> gpt-oss-120b is the stronger model overall, scoring 36.0 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-120b-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and phi-3-medium 14B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-120b leads 42.3 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for gpt-oss-120b and 27.6% for phi-3-medium 14B.

## Snapshot

| | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 36.0 | 29.1 |
| Rank | 210 | 306 |
| Context | 131K | — |
| Input $/M | $0.037 | — |
| Output $/M | $0.17 | — |
| Weights | Open | Open |

## Coding

- gpt-oss-120b: 33.2 (#251)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1380 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |

## Agentic & Tool Use

- gpt-oss-120b: 12.1 (#145)
- phi-3-medium 14B: —

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |

## Reasoning

- gpt-oss-120b: 19.5 (#236)
- phi-3-medium 14B: —

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 139.94 | 121.18 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| LMArena Hard Prompts | 1364 | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- gpt-oss-120b: 50.6 (#43)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
| LMArena Math | 1388 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- gpt-oss-120b: 42.3 (#89)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 75.8% | 27.6% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
| LMArena Expert | 1356 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- gpt-oss-120b: 48.2 (#142)
- phi-3-medium 14B: —

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1350 | — |
| LMArena Chinese | 1384 | — |
| LMArena French | 1370 | — |
| LMArena German | 1355 | — |
| LMArena Japanese | 1332 | — |
| LMArena Korean | 1283 | — |
| LMArena Russian | 1343 | — |
| LMArena Spanish | 1388 | — |

## Instruction Following

- gpt-oss-120b: 69.5 (#168)
- phi-3-medium 14B: —

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| IFEval | 83.6% | — |
| LMArena Instruction Following | 1318 | — |

## Long Context

- gpt-oss-120b: 31.4 (#273)
- phi-3-medium 14B: —

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1319 | — |

## Writing & Preference

- gpt-oss-120b: 46.7 (#213)
- phi-3-medium 14B: —

| Benchmark | gpt-oss-120b | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1366 | — |
| LMArena Creative Writing | 1274 | — |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| LMArena Multi-Turn | 1340 | — |

## FAQ

### Is gpt-oss-120b better than phi-3-medium 14B?

gpt-oss-120b is the stronger model overall, scoring 36.0 to 29.1 on the Noometry Index.

### Is gpt-oss-120b or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 33.2 in the Noometry coding category.

### How many benchmarks do gpt-oss-120b and phi-3-medium 14B share?

2 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and phi-3-medium 14B has 13.