Model comparison
GPT-5 Pro vs Llama 3.2 90B
GPT-5 Pro is the stronger model overall, scoring 46.4 to 27.5 on the Noometry Index.
Last verified . 2 shared benchmarks.
MetaSummary
- They share 2 benchmarks with published results for both. GPT-5 Pro scores higher in 3 categories and Llama 3.2 90B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Pro leads 48.5 to 11.1.
- The biggest single-benchmark swing is EnigmaEval: 18.8% for GPT-5 Pro and 0.4% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Pro | Llama 3.2 90B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 46.4 | 27.5 |
| Released | 2025-10-06 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 272K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $120 | — |
| Results tracked | 12 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5 Pro: 44.0 (#80), Llama 3.2 90B: —
Agentic & Tool Use Not comparable
GPT-5 Pro: —, Llama 3.2 90B: 30.0 (#80)
| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 38.9 (#62), Llama 3.2 90B: 21.7 (#217)
| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | 18.8% | 0.4% |
| Epoch Capabilities Index | 150.28 | 125.5 |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| ARC-AGI-1 | 70.2% | — |
Math GPT-5 Pro leads
GPT-5 Pro: 48.5 (#63), Llama 3.2 90B: 11.1 (#308)
| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| MATH Level 5 | — | 39.4% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.7 (#42), Llama 3.2 90B: 21.7 (#274)
| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| Humanity's Last Exam | 31.6% | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
GPT-5 Pro: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Frequently asked questions
Is GPT-5 Pro better than Llama 3.2 90B?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 27.5 on the Noometry Index.
How many benchmarks do GPT-5 Pro and Llama 3.2 90B share?
2 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Llama 3.2 90B has 9.