# Olmo 3 32b Think vs Phi 3 Medium 4k Instruct

> Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-3-32b-think-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Olmo 3 32b Think scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3 32b Think leads 49.1 to 34.1.

## Snapshot

| | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 38.7 | 33.0 |
| Rank | 183 | 250 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Olmo 3 32b Think: 38.6 (#172)
- Phi 3 Medium 4k Instruct: 32.9 (#268)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1319 | 1130 |

## Reasoning

- Olmo 3 32b Think: 25.9 (#140)
- Phi 3 Medium 4k Instruct: 21.7 (#214)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1127 |

## Math

- Olmo 3 32b Think: 36.5 (#165)
- Phi 3 Medium 4k Instruct: 33.4 (#202)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1316 | 1173 |

## Knowledge

- Olmo 3 32b Think: 35.0 (#190)
- Phi 3 Medium 4k Instruct: 30.2 (#229)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1273 | 1108 |

## Multilingual

- Olmo 3 32b Think: 41.2 (#210)
- Phi 3 Medium 4k Instruct: 30.6 (#263)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1255 | 1094 |
| LMArena Chinese | 1300 | 1108 |
| LMArena French | 1291 | 1110 |
| LMArena German | 1290 | 1101 |
| LMArena Russian | 1254 | 1145 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |

## Instruction Following

- Olmo 3 32b Think: 67.2 (#198)
- Phi 3 Medium 4k Instruct: 57.6 (#268)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1275 | 1113 |

## Long Context

- Olmo 3 32b Think: 39.4 (#182)
- Phi 3 Medium 4k Instruct: 34.0 (#255)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1296 | 1120 |

## Writing & Preference

- Olmo 3 32b Think: 49.1 (#193)
- Phi 3 Medium 4k Instruct: 34.1 (#272)

| Benchmark | Olmo 3 32b Think | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1300 | 1138 |
| LMArena Creative Writing | 1256 | 1107 |
| LMArena Multi-Turn | 1290 | 1088 |

## FAQ

### Is Olmo 3 32b Think better than Phi 3 Medium 4k Instruct?

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 33.0 on the Noometry Index.

### Is Olmo 3 32b Think or Phi 3 Medium 4k Instruct better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 32.9 in the Noometry coding category.

### How many benchmarks do Olmo 3 32b Think and Phi 3 Medium 4k Instruct share?

14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.