# GPT-5.2 Codex vs Olmo 7b Instruct

> GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-olmo-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.4 to 29.1.
- Olmo 7b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 42.2 | 29.7 |
| Rank | 107 | 293 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.4 (#66)
- Olmo 7b Instruct: 29.1 (#298)

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1016 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 40.7 (#20)
- Olmo 7b Instruct: —

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- Olmo 7b Instruct: 18.0 (#273)

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 993 |

## Math

- GPT-5.2 Codex: —
- Olmo 7b Instruct: 27.8 (#234)

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| LMArena Math | — | 1018 |

## Multilingual

- GPT-5.2 Codex: —
- Olmo 7b Instruct: 24.1 (#286)

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| LMArena Non-English | — | 977 |
| LMArena Chinese | — | 1013 |
| LMArena Russian | — | 946 |

## Instruction Following

- GPT-5.2 Codex: —
- Olmo 7b Instruct: 49.3 (#296)

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 978 |

## Writing & Preference

- GPT-5.2 Codex: —
- Olmo 7b Instruct: 26.0 (#298)

| Benchmark | GPT-5.2 Codex | Olmo 7b Instruct |
|---|---|---|
| LMArena Text | — | 1032 |
| LMArena Creative Writing | — | 990 |
| LMArena Multi-Turn | — | 1007 |

## FAQ

### Is GPT-5.2 Codex better than Olmo 7b Instruct?

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 29.7 on the Noometry Index.

### Is GPT-5.2 Codex or Olmo 7b Instruct better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 29.1 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and Olmo 7b Instruct share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Olmo 7b Instruct has 10.