# Llama 3.2 90B vs o1

> o1 is the stronger model overall, scoring 40.9 to 27.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-o1
- Last updated: 2026-10-11
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Llama 3.2 90B scores higher in 1 category and o1 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where o1 leads 36.1 to 11.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 73.3% for o1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3.2 90B | o1 |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 27.5 | 40.9 |
| Rank | 331 | 143 |
| Context | — | 200K |
| Input $/M | — | $15 |
| Output $/M | — | $60 |
| Weights | Open | Proprietary |

## Coding

- Llama 3.2 90B: —
- o1: 46.1 (#70)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| LMArena Coding | — | 1367 |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |

## Agentic & Tool Use

- Llama 3.2 90B: 30.0 (#80)
- o1: 24.6 (#117)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| Cybench | — | 10% |
| BALROG | 27.3% | — |
| METR Time Horizons | — | 51.1% |

## Reasoning

- Llama 3.2 90B: 21.7 (#217)
- o1: 27.9 (#111)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| EnigmaEval | 0.4% | 5.7% |
| Epoch Capabilities Index | 125.5 | 141.91 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| LiveBench Reasoning | — | 91.6% |
| LMArena Hard Prompts | — | 1371 |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |

## Math

- Llama 3.2 90B: 11.1 (#308)
- o1: 36.1 (#175)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 73.3% |
| MATH Level 5 | 39.4% | 94.7% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| LiveBench Math | — | 80.3% |
| LMArena Math | — | 1388 |
| FrontierMath (Feb 2025 set) | — | 9.3% |

## Knowledge

- Llama 3.2 90B: 21.7 (#274)
- o1: 41.5 (#110)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| GPQA Diamond | 41% | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| LMArena Expert | — | 1361 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 25.4 (#124)
- o1: 34.2 (#93)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| LMArena Vision | 1000 | 1168 |
| GeoBench | 52% | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- Llama 3.2 90B: —
- o1: 48.6 (#142)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| LMArena Non-English | — | 1358 |
| LMArena Chinese | — | 1394 |
| LMArena French | — | 1344 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Russian | — | 1356 |
| LMArena Spanish | — | 1345 |

## Instruction Following

- Llama 3.2 90B: —
- o1: 74.8 (#86)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| LiveBench Instruction Following | — | 81.5% |
| LMArena Instruction Following | — | 1367 |

## Long Context

- Llama 3.2 90B: —
- o1: 50.3 (#9)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1378 |

## Writing & Preference

- Llama 3.2 90B: —
- o1: 55.6 (#144)

| Benchmark | Llama 3.2 90B | o1 |
|---|---|---|
| LMArena Text | — | 1366 |
| LMArena Creative Writing | — | 1348 |
| Short-Story Creative Writing | — | 70.2% |
| LMArena Multi-Turn | — | 1369 |
| LiveBench Language | — | 65.4% |

## FAQ

### Is Llama 3.2 90B better than o1?

o1 is the stronger model overall, scoring 40.9 to 27.5 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and o1 share?

7 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and o1 has 52.