# Llama 3.2 90B vs Olmo 3.1 32b Instruct

> Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-olmo-3-1-32b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Olmo 3.1 32b Instruct leads 33.6 to 10.4.

## Snapshot

| | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 27.1 | 38.8 |
| Rank | 326 | 168 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 90B: —
- Olmo 3.1 32b Instruct: 38.9 (#154)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | — | 1346 |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- Olmo 3.1 32b Instruct: —

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- Olmo 3.1 32b Instruct: 25.4 (#131)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1322 |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- Olmo 3.1 32b Instruct: 33.6 (#169)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1305 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- Olmo 3.1 32b Instruct: 35.4 (#175)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1307 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- Olmo 3.1 32b Instruct: —

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- Olmo 3.1 32b Instruct: 42.8 (#185)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | — | 1275 |
| LMArena Chinese | — | 1304 |
| LMArena French | — | 1328 |
| LMArena German | — | 1283 |
| LMArena Korean | — | 1206 |
| LMArena Russian | — | 1268 |
| LMArena Spanish | — | 1337 |

## Instruction Following

- Llama 3.2 90B: —
- Olmo 3.1 32b Instruct: 68.8 (#182)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1298 |

## Long Context

- Llama 3.2 90B: —
- Olmo 3.1 32b Instruct: 39.9 (#161)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1312 |

## Writing & Preference

- Llama 3.2 90B: —
- Olmo 3.1 32b Instruct: 50.4 (#179)

| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | — | 1311 |
| LMArena Creative Writing | — | 1264 |
| LMArena Multi-Turn | — | 1309 |

## FAQ

### Is Llama 3.2 90B better than Olmo 3.1 32b Instruct?

Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and Olmo 3.1 32b Instruct share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Olmo 3.1 32b Instruct has 16.