# Amazon Nova Experimental Chat 26 02 10 vs Phi 3 Mini 4k Instruct

> Amazon Nova Experimental Chat 26 02 10 is the stronger model overall, scoring 43.8 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-26-02-10-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Amazon Nova Experimental Chat 26 02 10 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Experimental Chat 26 02 10 leads 62.0 to 27.7.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 43.8 | 27.4 |
| Rank | 77 | 324 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Experimental Chat 26 02 10: 43.2 (#81)
- Phi 3 Mini 4k Instruct: 26.1 (#319)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1483 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Amazon Nova Experimental Chat 26 02 10: 28.9 (#84)
- Phi 3 Mini 4k Instruct: 13.6 (#326)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1458 | 1072 |
| 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

- Amazon Nova Experimental Chat 26 02 10: 36.6 (#108)
- Phi 3 Mini 4k Instruct: 24.5 (#258)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1440 | 1111 |
| LiveBench Math | — | 15.7% |

## Knowledge

- Amazon Nova Experimental Chat 26 02 10: 41.6 (#98)
- Phi 3 Mini 4k Instruct: 27.9 (#241)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1505 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- Amazon Nova Experimental Chat 26 02 10: 54.3 (#48)
- Phi 3 Mini 4k Instruct: 26.5 (#275)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1435 | 1021 |
| LMArena Chinese | 1465 | 1021 |
| LMArena Russian | 1423 | 1022 |
| LMArena French | — | 1075 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1084 |

## Instruction Following

- Amazon Nova Experimental Chat 26 02 10: 75.3 (#66)
- Phi 3 Mini 4k Instruct: 48.0 (#298)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1426 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- Amazon Nova Experimental Chat 26 02 10: 44.0 (#73)
- Phi 3 Mini 4k Instruct: 31.7 (#271)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1441 | 1044 |

## Writing & Preference

- Amazon Nova Experimental Chat 26 02 10: 62.0 (#80)
- Phi 3 Mini 4k Instruct: 27.7 (#295)

| Benchmark | Amazon Nova Experimental Chat 26 02 10 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1449 | 1073 |
| LMArena Creative Writing | 1369 | 1037 |
| LMArena Multi-Turn | 1442 | 1018 |
| LiveBench Language | — | 9.2% |

## FAQ

### Is Amazon Nova Experimental Chat 26 02 10 better than Phi 3 Mini 4k Instruct?

Amazon Nova Experimental Chat 26 02 10 is the stronger model overall, scoring 43.8 to 27.4 on the Noometry Index.

### Is Amazon Nova Experimental Chat 26 02 10 or Phi 3 Mini 4k Instruct better for coding?

Amazon Nova Experimental Chat 26 02 10 scores higher on coding benchmarks: 43.2 versus 26.1 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 26 02 10 and Phi 3 Mini 4k Instruct share?

12 benchmarks have published results for both models. Amazon Nova Experimental Chat 26 02 10 has 12 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.