# GPT-5.3 Chat vs Llama 3.2 90B

> GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 27.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-3-chat-vs-llama-3-2-90b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where GPT-5.3 Chat leads 38.2 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 42.8 | 27.5 |
| Rank | 109 | 331 |
| Context | 128K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Chat: 41.4 (#124)
- Llama 3.2 90B: —

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| LMArena Coding | 1408 | — |

## Agentic & Tool Use

- GPT-5.3 Chat: —
- Llama 3.2 90B: 30.0 (#80)

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- GPT-5.3 Chat: 28.5 (#102)
- Llama 3.2 90B: 21.7 (#217)

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1399 | — |
| Epoch Capabilities Index | — | 125.5 |

## Math

- GPT-5.3 Chat: 38.2 (#142)
- Llama 3.2 90B: 11.1 (#308)

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1389 | — |
| MATH Level 5 | — | 39.4% |

## Knowledge

- GPT-5.3 Chat: 38.8 (#140)
- Llama 3.2 90B: 21.7 (#274)

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| LMArena Expert | 1397 | — |
| MMLU | — | 80.3% |

## Multimodal

- GPT-5.3 Chat: —
- Llama 3.2 90B: 25.4 (#124)

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- GPT-5.3 Chat: 50.3 (#124)
- Llama 3.2 90B: —

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1382 | — |
| LMArena Chinese | 1432 | — |
| LMArena French | 1397 | — |
| LMArena German | 1384 | — |
| LMArena Japanese | 1352 | — |
| LMArena Korean | 1346 | — |
| LMArena Russian | 1400 | — |
| LMArena Spanish | 1371 | — |

## Instruction Following

- GPT-5.3 Chat: 72.8 (#129)
- Llama 3.2 90B: —

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1378 | — |

## Long Context

- GPT-5.3 Chat: 42.6 (#120)
- Llama 3.2 90B: —

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1396 | — |

## Writing & Preference

- GPT-5.3 Chat: 63.1 (#68)
- Llama 3.2 90B: —

| Benchmark | GPT-5.3 Chat | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1389 | — |
| LMArena Creative Writing | 1355 | — |
| EQ-Bench Creative Writing | 1690 | — |
| LMArena Multi-Turn | 1412 | — |

## FAQ

### Is GPT-5.3 Chat better than Llama 3.2 90B?

GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 27.5 on the Noometry Index.

### How many benchmarks do GPT-5.3 Chat and Llama 3.2 90B share?

0 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Llama 3.2 90B has 9.