# Mistral Large vs Phi 3 Small 8k Instruct

> Mistral Large is the stronger model overall, scoring 31.9 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Mistral Large scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Large leads 67.9 to 51.9.
- The biggest single-benchmark swing is LiveBench Reasoning: 43.5% for Mistral Large and 15.9% for Phi 3 Small 8k Instruct.

## Snapshot

| | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.9 | 29.3 |
| Rank | 263 | 314 |
| Context | 131K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Open | Open |

## Coding

- Mistral Large: 34.3 (#240)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 47.1% | 20.3% |
| LMArena Coding | 1277 | 1101 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |

## Agentic & Tool Use

- Mistral Large: 28.6 (#89)
- Phi 3 Small 8k Instruct: —

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |

## Reasoning

- Mistral Large: 15.8 (#310)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 43.5% | 15.9% |
| LMArena Hard Prompts | 1257 | 1100 |
| LiveBench Data Analysis | 50.1% | 30.3% |
| LiveBench | 48.4% | 24% |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| DTBench | 65.1% | — |
| LMCA | 16.7% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |

## Math

- Mistral Large: 18.2 (#291)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 42.5% | 17.6% |
| LMArena Math | 1262 | 1151 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Large: 30.1 (#230)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1232 | 1067 |
| MMLU | 80% | 75.7% |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- Mistral Large: 40.0 (#219)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1237 | 1058 |
| LMArena Chinese | 1240 | 1061 |
| LMArena French | 1325 | 1135 |
| LMArena German | 1254 | 1080 |
| LMArena Japanese | 1188 | 966 |
| LMArena Korean | 1202 | 894 |
| LMArena Russian | 1257 | 1111 |
| LMArena Spanish | 1268 | 1111 |

## Instruction Following

- Mistral Large: 67.9 (#191)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 67.9% | 47.2% |
| LMArena Instruction Following | 1249 | 1087 |
| IFEval | 87.7% | — |

## Long Context

- Mistral Large: 38.3 (#199)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1261 | 1088 |

## Writing & Preference

- Mistral Large: 40.7 (#242)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | Mistral Large | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1266 | 1110 |
| LMArena Creative Writing | 1243 | 1083 |
| LMArena Multi-Turn | 1260 | 1068 |
| LiveBench Language | 39.4% | 12.9% |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |

## FAQ

### Is Mistral Large better than Phi 3 Small 8k Instruct?

Mistral Large is the stronger model overall, scoring 31.9 to 29.3 on the Noometry Index.

### Is Mistral Large or Phi 3 Small 8k Instruct better for coding?

Mistral Large scores higher on coding benchmarks: 34.3 versus 27.9 in the Noometry coding category.

### How many benchmarks do Mistral Large and Phi 3 Small 8k Instruct share?

25 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Phi 3 Small 8k Instruct has 32.