Model comparison
GPT-5.3 Codex vs Llama 3.2 90B
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 27.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
MetaSummary
- They share 1 benchmark with published results for both. GPT-5.3 Codex scores higher in 1 category and Llama 3.2 90B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 30.0.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | Llama 3.2 90B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 45.8 | 27.5 |
| Released | 2026-02-05 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 8 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.3 Codex: 48.6 (#56), Llama 3.2 90B: —
| Benchmark | GPT-5.3 Codex | Llama 3.2 90B |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1409 | — |
| WeirdML | 79.3% | — |
| ALE-Bench | 1,655 | — |
Agentic & Tool Use GPT-5.3 Codex leads
GPT-5.3 Codex: 48.0 (#9), Llama 3.2 90B: 30.0 (#80)
| Benchmark | GPT-5.3 Codex | Llama 3.2 90B |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| BALROG | — | 27.3% |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Llama 3.2 90B: 21.7 (#217)
| Benchmark | GPT-5.3 Codex | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 156.77 | 125.5 |
| EnigmaEval | — | 0.4% |
Math Not comparable
GPT-5.3 Codex: —, Llama 3.2 90B: 11.1 (#308)
| Benchmark | GPT-5.3 Codex | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| MATH Level 5 | — | 39.4% |
Knowledge Not comparable
GPT-5.3 Codex: —, Llama 3.2 90B: 21.7 (#274)
| Benchmark | GPT-5.3 Codex | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| MMLU | — | 80.3% |
Multimodal Not comparable
GPT-5.3 Codex: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | GPT-5.3 Codex | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Frequently asked questions
Is GPT-5.3 Codex better than Llama 3.2 90B?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 27.5 on the Noometry Index.
How many benchmarks do GPT-5.3 Codex and Llama 3.2 90B share?
1 benchmark has published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Llama 3.2 90B has 9.