# GPT-5.2 Codex vs phi-3-medium 14B

> GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-phi-3-medium-14b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 36.8.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | phi-3-medium 14B |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 42.6 | 29.7 |
| Rank | 111 | 306 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.5 (#71)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | GPT-5.2 Codex | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 41.0 (#22)
- phi-3-medium 14B: —

| Benchmark | GPT-5.2 Codex | phi-3-medium 14B |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- phi-3-medium 14B: —

| Benchmark | GPT-5.2 Codex | phi-3-medium 14B |
|---|---|---|
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- GPT-5.2 Codex: —
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | GPT-5.2 Codex | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |

## Knowledge

- GPT-5.2 Codex: —
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | GPT-5.2 Codex | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## FAQ

### Is GPT-5.2 Codex better than phi-3-medium 14B?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 29.7 on the Noometry Index.

### Is GPT-5.2 Codex or phi-3-medium 14B better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 36.8 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and phi-3-medium 14B share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and phi-3-medium 14B has 13.