# Llama 3.2 90B vs Olmo 3 32b Think

> Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 27.1 on the Noometry Index.

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

## Summary

- The widest gap is in math, where Olmo 3 32b Think leads 33.8 to 10.4.

## Snapshot

| | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 27.1 | 38.1 |
| Rank | 326 | 182 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 90B: —
- Olmo 3 32b Think: 38.0 (#169)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | — | 1318 |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- Olmo 3 32b Think: —

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- Olmo 3 32b Think: 24.9 (#138)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1302 |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- Olmo 3 32b Think: 33.8 (#165)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1315 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- Olmo 3 32b Think: 34.4 (#189)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1272 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- Olmo 3 32b Think: —

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- Olmo 3 32b Think: 41.4 (#205)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | — | 1255 |
| LMArena Chinese | — | 1300 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
| LMArena Russian | — | 1255 |

## Instruction Following

- Llama 3.2 90B: —
- Olmo 3 32b Think: 67.4 (#193)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | — | 1275 |

## Long Context

- Llama 3.2 90B: —
- Olmo 3 32b Think: 39.4 (#177)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | — | 1296 |

## Writing & Preference

- Llama 3.2 90B: —
- Olmo 3 32b Think: 49.2 (#188)

| Benchmark | Llama 3.2 90B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | — | 1300 |
| LMArena Creative Writing | — | 1256 |
| LMArena Multi-Turn | — | 1289 |

## FAQ

### Is Llama 3.2 90B better than Olmo 3 32b Think?

Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and Olmo 3 32b Think share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Olmo 3 32b Think has 14.