# OLMo 2 Furious 13B vs Phi 3 Mini 4k Instruct

> OLMo 2 Furious 13B is the stronger model overall, scoring 29.2 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-2-furious-13b-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. OLMo 2 Furious 13B scores higher in 4 categories and Phi 3 Mini 4k Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where OLMo 2 Furious 13B leads 43.0 to 27.7.
- The biggest single-benchmark swing is LiveBench Instruction Following: 60.6% for OLMo 2 Furious 13B and 39.1% for Phi 3 Mini 4k Instruct.

## Snapshot

| | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 29.2 | 27.4 |
| Rank | 301 | 324 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- OLMo 2 Furious 13B: 28.1 (#309)
- Phi 3 Mini 4k Instruct: 26.1 (#319)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 10.4% | 15.5% |
| LMArena Coding | — | 1093 |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- OLMo 2 Furious 13B: 14.8 (#312)
- Phi 3 Mini 4k Instruct: 13.6 (#326)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 16.3% | 26.8% |
| LiveBench Data Analysis | 20.6% | 34.7% |
| LiveBench | 22.1% | 22.4% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1072 |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |

## Math

- OLMo 2 Furious 13B: 21.3 (#270)
- Phi 3 Mini 4k Instruct: 24.5 (#258)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 13.6% | 15.7% |
| Omni-MATH | 15.6% | — |
| LMArena Math | — | 1111 |

## Knowledge

- OLMo 2 Furious 13B: 18.0 (#278)
- Phi 3 Mini 4k Instruct: 27.9 (#241)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| MMLU-Pro | 31% | — |
| GPQA (HELM) | 31.6% | — |
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- OLMo 2 Furious 13B: —
- Phi 3 Mini 4k Instruct: 26.5 (#275)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1075 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1084 |

## Instruction Following

- OLMo 2 Furious 13B: 61.1 (#243)
- Phi 3 Mini 4k Instruct: 48.0 (#298)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 60.6% | 39.1% |
| IFEval | 73% | — |
| LMArena Instruction Following | — | 1053 |

## Long Context

- OLMo 2 Furious 13B: —
- Phi 3 Mini 4k Instruct: 31.7 (#271)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |

## Writing & Preference

- OLMo 2 Furious 13B: 43.0 (#226)
- Phi 3 Mini 4k Instruct: 27.7 (#295)

| Benchmark | OLMo 2 Furious 13B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Language | 11.2% | 9.2% |
| LMArena Text | — | 1073 |
| LMArena Creative Writing | — | 1037 |
| WildBench | 68.9% | — |
| LMArena Multi-Turn | — | 1018 |

## FAQ

### Is OLMo 2 Furious 13B better than Phi 3 Mini 4k Instruct?

OLMo 2 Furious 13B is the stronger model overall, scoring 29.2 to 27.4 on the Noometry Index.

### Is OLMo 2 Furious 13B or Phi 3 Mini 4k Instruct better for coding?

OLMo 2 Furious 13B scores higher on coding benchmarks: 28.1 versus 26.1 in the Noometry coding category.

### How many benchmarks do OLMo 2 Furious 13B and Phi 3 Mini 4k Instruct share?

7 benchmarks have published results for both models. OLMo 2 Furious 13B has 12 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.