# GPT-5 Pro vs Llama 3.2 90B

> GPT-5 Pro is the stronger model overall, scoring 46.2 to 27.1 on the Noometry Index.

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

## Summary

- 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 48.0 to 10.4.
- 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.

## Snapshot

| | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 46.2 | 27.1 |
| Rank | 58 | 326 |
| Context | 400K | — |
| Input $/M | $15 | — |
| Output $/M | $120 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Pro: 43.4 (#77)
- Llama 3.2 90B: —

| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| WeirdML | 60.4% | — |
| AlgoTune | 1.31 | — |

## Agentic & Tool Use

- GPT-5 Pro: —
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- GPT-5 Pro: 39.2 (#52)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | 18.8% | 0.4% |
| Epoch Capabilities Index | 150.26 | 125.5 |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| ARC-AGI-1 | 70.2% | — |

## Math

- GPT-5 Pro: 48.0 (#53)
- Llama 3.2 90B: 10.4 (#302)

| 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: 56.2 (#39)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| Humanity's Last Exam | 31.6% | — |
| MMLU | — | 80.3% |

## Multimodal

- GPT-5 Pro: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | GPT-5 Pro | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## FAQ

### Is GPT-5 Pro better than Llama 3.2 90B?

GPT-5 Pro is the stronger model overall, scoring 46.2 to 27.1 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.