# GPT-5.2 Codex vs Nova 2 Lite

> GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 39.0 on the Noometry Index. Nova 2 Lite costs 5.7× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-nova-2-lite
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 40.7 to 23.9.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- Nova 2 Lite accepts more context: 1M tokens versus 400K.

## Snapshot

| | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 42.2 | 39.0 |
| Rank | 107 | 161 |
| Context | 400K | 1M |
| Input $/M | $1.75 | $0.30 |
| Output $/M | $14 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Codex: 45.4 (#66)
- Nova 2 Lite: 40.1 (#131)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1386 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 40.7 (#20)
- Nova 2 Lite: 23.9 (#114)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |

## Reasoning

- GPT-5.2 Codex: —
- Nova 2 Lite: 26.4 (#120)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | — | 1364 |

## Math

- GPT-5.2 Codex: —
- Nova 2 Lite: 34.8 (#154)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| LMArena Math | — | 1359 |

## Knowledge

- GPT-5.2 Codex: —
- Nova 2 Lite: 42.5 (#88)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1360 |

## Multilingual

- GPT-5.2 Codex: —
- Nova 2 Lite: 47.3 (#148)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | — | 1337 |
| LMArena Chinese | — | 1364 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1273 |
| LMArena Korean | — | 1284 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1372 |

## Instruction Following

- GPT-5.2 Codex: —
- Nova 2 Lite: 70.7 (#156)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | — | 1335 |

## Long Context

- GPT-5.2 Codex: —
- Nova 2 Lite: 40.6 (#145)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | — | 1335 |

## Writing & Preference

- GPT-5.2 Codex: —
- Nova 2 Lite: 54.1 (#150)

| Benchmark | GPT-5.2 Codex | Nova 2 Lite |
|---|---|---|
| LMArena Text | — | 1362 |
| LMArena Creative Writing | — | 1291 |
| LMArena Multi-Turn | — | 1338 |

## FAQ

### Is GPT-5.2 Codex better than Nova 2 Lite?

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 39.0 on the Noometry Index. Nova 2 Lite costs 5.7× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.2 Codex or Nova 2 Lite?

Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

### Is GPT-5.2 Codex or Nova 2 Lite better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 400K.

### How many benchmarks do GPT-5.2 Codex and Nova 2 Lite share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Nova 2 Lite has 19.