# Olmo 2 0325 32b Instruct vs Phi-4

> Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-2-0325-32b-instruct-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 5 categories and Phi-4 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.5 to 19.2.

## Snapshot

| | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 32.2 | 30.9 |
| Rank | 248 | 269 |
| Context | — | 128K |
| Input $/M | — | $0.07 |
| Output $/M | — | $0.14 |
| Weights | Open | Open |

## Coding

- Olmo 2 0325 32b Instruct: 34.6 (#222)
- Phi-4: 33.8 (#237)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Coding | 1210 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- Olmo 2 0325 32b Instruct: —
- Phi-4: 22.6 (#120)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Olmo 2 0325 32b Instruct: 22.6 (#174)
- Phi-4: 17.0 (#287)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1220 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.43 |
| LiveBench | — | 41.6% |

## Math

- Olmo 2 0325 32b Instruct: 24.8 (#255)
- Phi-4: 19.6 (#279)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Math | 1208 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| Omni-MATH | 16.1% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Olmo 2 0325 32b Instruct: 19.2 (#274)
- Phi-4: 32.5 (#204)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| MMLU-Pro | 41.4% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| GPQA (HELM) | 28.7% | — |
| LMArena Expert | — | 1203 |
| MMLU | — | 84.8% |

## Multilingual

- Olmo 2 0325 32b Instruct: 35.0 (#243)
- Phi-4: 37.4 (#232)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Non-English | 1160 | 1197 |
| LMArena Chinese | 1192 | 1211 |
| LMArena Russian | 1187 | 1209 |
| LMArena French | — | 1223 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Spanish | — | 1234 |

## Instruction Following

- Olmo 2 0325 32b Instruct: 61.8 (#238)
- Phi-4: 60.6 (#246)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1186 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
| IFEval | 78% | — |

## Long Context

- Olmo 2 0325 32b Instruct: 36.2 (#229)
- Phi-4: 36.9 (#221)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1194 | 1217 |

## Writing & Preference

- Olmo 2 0325 32b Instruct: 42.3 (#231)
- Phi-4: 40.7 (#239)

| Benchmark | Olmo 2 0325 32b Instruct | Phi-4 |
|---|---|---|
| LMArena Text | 1218 | 1217 |
| LMArena Creative Writing | 1199 | 1182 |
| LMArena Multi-Turn | 1221 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| WildBench | 73.4% | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Olmo 2 0325 32b Instruct better than Phi-4?

Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 30.9 on the Noometry Index.

### Is Olmo 2 0325 32b Instruct or Phi-4 better for coding?

They score almost the same on coding (34.6 vs 33.8); test both on your own repository before choosing.

### How many benchmarks do Olmo 2 0325 32b Instruct and Phi-4 share?

11 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Phi-4 has 37.