# GPT-5.5 Instant vs Phi 3 Mini 128k Instruct

> GPT-5.5 Instant is the stronger model overall, scoring 42.5 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-5-instant-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-5.5 Instant scores higher in 7 categories and Phi 3 Mini 128k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.5 Instant leads 62.0 to 27.3.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 42.5 | 29.1 |
| Rank | 99 | 303 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.5 Instant: 43.7 (#73)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1433 | 1040 |
| SciCode | 48.6% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |

## Reasoning

- GPT-5.5 Instant: 24.2 (#149)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1028 |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| Epoch Capabilities Index | 142.48 | — |

## Math

- GPT-5.5 Instant: 26.1 (#241)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1420 | 1089 |
| FrontierMath (Tiers 1-3) | 26.3% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 68.1% | — |

## Knowledge

- GPT-5.5 Instant: 48.9 (#68)
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1409 | 984 |
| GPQA Diamond | 82.5% | — |

## Multimodal

- GPT-5.5 Instant: 39.3 (#48)
- Phi 3 Mini 128k Instruct: —

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 1250 | — |
| LMArena Document | 1403 | — |

## Multilingual

- GPT-5.5 Instant: 53.0 (#76)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1417 | 1000 |
| LMArena Chinese | 1457 | 1016 |
| LMArena French | 1428 | 1038 |
| LMArena German | 1410 | 1006 |
| LMArena Japanese | 1408 | 899 |
| LMArena Korean | 1393 | 856 |
| LMArena Russian | 1430 | 1004 |
| LMArena Spanish | 1430 | 1058 |

## Instruction Following

- GPT-5.5 Instant: 74.4 (#94)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1407 | 1023 |

## Long Context

- GPT-5.5 Instant: 43.4 (#92)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 996 |

## Writing & Preference

- GPT-5.5 Instant: 62.0 (#81)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | GPT-5.5 Instant | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1419 | 1050 |
| LMArena Creative Writing | 1420 | 1024 |
| LMArena Multi-Turn | 1434 | 989 |

## FAQ

### Is GPT-5.5 Instant better than Phi 3 Mini 128k Instruct?

GPT-5.5 Instant is the stronger model overall, scoring 42.5 to 29.1 on the Noometry Index.

### Is GPT-5.5 Instant or Phi 3 Mini 128k Instruct better for coding?

GPT-5.5 Instant scores higher on coding benchmarks: 43.7 versus 28.3 in the Noometry coding category.

### How many benchmarks do GPT-5.5 Instant and Phi 3 Mini 128k Instruct share?

17 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.