# Phi 3 Mini 4k Instruct vs Tulu 3 (Tülu 3) 70B

> Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-4k-instruct-vs-tulu-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.8 to 27.7.

## Snapshot

| | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Provider | Microsoft | Allen Institute for AI (Ai2) |
| Noometry Index | 27.4 | 32.6 |
| Rank | 324 | 242 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 4k Instruct: 26.1 (#319)
- Tulu 3 (Tülu 3) 70B: 35.4 (#211)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1093 | 1236 |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |

## Reasoning

- Phi 3 Mini 4k Instruct: 13.6 (#326)
- Tulu 3 (Tülu 3) 70B: 22.9 (#172)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1220 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |

## Math

- Phi 3 Mini 4k Instruct: 24.5 (#258)
- Tulu 3 (Tülu 3) 70B: 13.3 (#297)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1111 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LiveBench Math | 15.7% | — |
| MATH Level 5 | — | 42.7% |

## Knowledge

- Phi 3 Mini 4k Instruct: 27.9 (#241)
- Tulu 3 (Tülu 3) 70B: 25.1 (#257)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1045 | — |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |

## Multilingual

- Phi 3 Mini 4k Instruct: 26.5 (#275)
- Tulu 3 (Tülu 3) 70B: 40.1 (#217)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1021 | 1236 |
| LMArena Chinese | 1021 | 1249 |
| LMArena Russian | 1022 | 1246 |
| LMArena French | 1075 | — |
| LMArena German | 1044 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Spanish | 1084 | — |

## Instruction Following

- Phi 3 Mini 4k Instruct: 48.0 (#298)
- Tulu 3 (Tülu 3) 70B: 65.0 (#222)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1053 | 1233 |
| LiveBench Instruction Following | 39.1% | — |

## Long Context

- Phi 3 Mini 4k Instruct: 31.7 (#271)
- Tulu 3 (Tülu 3) 70B: 37.1 (#217)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1044 | 1224 |

## Writing & Preference

- Phi 3 Mini 4k Instruct: 27.7 (#295)
- Tulu 3 (Tülu 3) 70B: 45.8 (#218)

| Benchmark | Phi 3 Mini 4k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1073 | 1256 |
| LMArena Creative Writing | 1037 | 1231 |
| LMArena Multi-Turn | 1018 | 1252 |
| LiveBench Language | 9.2% | — |

## FAQ

### Is Phi 3 Mini 4k Instruct better than Tulu 3 (Tülu 3) 70B?

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 27.4 on the Noometry Index.

### Is Phi 3 Mini 4k Instruct or Tulu 3 (Tülu 3) 70B better for coding?

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 26.1 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 4k Instruct and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.