# Mercury 2.5 vs Phi 3 Mini 4k Instruct

> Mercury 2.5 is the stronger model overall, scoring 33.5 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-5-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Mercury 2.5 leads 39.5 to 26.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 33.5 | 27.9 |
| Rank | 242 | 328 |
| Context | 260K | — |
| Input $/M | $0.04 | — |
| Output $/M | $0.15 | — |
| Weights | Proprietary | Open |

## Coding

- Mercury 2.5: 39.5 (#156)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| SciCode | 38.5% | — |
| LiveBench Coding | — | 15.5% |
| LMArena Coding | — | 1093 |
| ALE-Bench | 301.65 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Mercury 2.5: 22.4 (#193)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LMArena Hard Prompts | — | 1072 |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- Mercury 2.5: 23.3 (#272)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| ProofBench | 3% | — |
| LiveBench Math | — | 15.7% |
| LMArena Math | — | 1111 |

## Knowledge

- Mercury 2.5: —
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- Mercury 2.5: —
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |

## Instruction Following

- Mercury 2.5: —
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 39.1% |
| LMArena Instruction Following | — | 1053 |

## Long Context

- Mercury 2.5: —
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |

## Writing & Preference

- Mercury 2.5: —
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Mercury 2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | — | 1073 |
| LMArena Creative Writing | — | 1037 |
| LMArena Multi-Turn | — | 1018 |
| LiveBench Language | — | 9.2% |

## FAQ

### Is Mercury 2.5 better than Phi 3 Mini 4k Instruct?

Mercury 2.5 is the stronger model overall, scoring 33.5 to 27.9 on the Noometry Index.

### Is Mercury 2.5 or Phi 3 Mini 4k Instruct better for coding?

Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 26.6 in the Noometry coding category.

### How many benchmarks do Mercury 2.5 and Phi 3 Mini 4k Instruct share?

0 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.