# GPT-5.2 Codex vs Granite 3.1 2b Instruct

> GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 33.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-granite-3-1-2b-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 33.4.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 42.6 | 33.2 |
| Rank | 111 | 247 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.5 (#71)
- Granite 3.1 2b Instruct: 33.4 (#257)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1149 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 41.0 (#22)
- Granite 3.1 2b Instruct: —

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 22.0 (#209)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1138 |

## Math

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 33.1 (#206)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | — | 1159 |

## Knowledge

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 30.8 (#224)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1131 |

## Multilingual

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 29.1 (#269)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1068 |
| LMArena Chinese | — | 1139 |
| LMArena Russian | — | 1063 |

## Instruction Following

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 57.7 (#264)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1116 |

## Long Context

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 35.0 (#244)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1155 |

## Writing & Preference

- GPT-5.2 Codex: —
- Granite 3.1 2b Instruct: 34.1 (#274)

| Benchmark | GPT-5.2 Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | — | 1127 |
| LMArena Creative Writing | — | 1116 |
| LMArena Multi-Turn | — | 1099 |

## FAQ

### Is GPT-5.2 Codex better than Granite 3.1 2b Instruct?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 33.2 on the Noometry Index.

### Is GPT-5.2 Codex or Granite 3.1 2b Instruct better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 33.4 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and Granite 3.1 2b Instruct share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Granite 3.1 2b Instruct has 12.