# GPT-5.4 Pro vs Llama 3.2 90B

> GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 27.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-pro-vs-llama-3-2-90b
- Last updated: 2026-10-12
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-5.4 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-5.4 Pro leads 72.4 to 11.1.
- The biggest single-benchmark swing is GPQA Diamond: 94.6% for GPT-5.4 Pro and 41% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 58.9 | 27.5 |
| Rank | 18 | 331 |
| Context | 1.05M | — |
| Input $/M | $30 | — |
| Output $/M | $180 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 Pro: 43.2 (#90)
- Llama 3.2 90B: —

| Benchmark | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| WeirdML | 57.4% | — |

## Agentic & Tool Use

- GPT-5.4 Pro: —
- Llama 3.2 90B: 30.0 (#80)

| Benchmark | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- GPT-5.4 Pro: 70.7 (#13)
- Llama 3.2 90B: 21.7 (#217)

| Benchmark | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | 23.8% | 0.4% |
| Epoch Capabilities Index | 158.93 | 125.5 |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |

## Math

- GPT-5.4 Pro: 72.4 (#22)
- Llama 3.2 90B: 11.1 (#308)

| Benchmark | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| MATH Level 5 | — | 39.4% |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |

## Knowledge

- GPT-5.4 Pro: 68.3 (#7)
- Llama 3.2 90B: 21.7 (#274)

| Benchmark | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 94.6% | 41% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| MMLU | — | 80.3% |

## Multimodal

- GPT-5.4 Pro: —
- Llama 3.2 90B: 25.4 (#124)

| Benchmark | GPT-5.4 Pro | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## FAQ

### Is GPT-5.4 Pro better than Llama 3.2 90B?

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 27.5 on the Noometry Index.

### How many benchmarks do GPT-5.4 Pro and Llama 3.2 90B share?

3 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Llama 3.2 90B has 9.