# GPT-5.6 Sol vs phi-3-medium 14B

> GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-6-sol-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. GPT-5.6 Sol scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Sol leads 85.5 to 25.2.
- The biggest single-benchmark swing is GPQA Diamond: 93.5% for GPT-5.6 Sol and 27.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 64.4 | 29.1 |
| Rank | 6 | 306 |
| Context | 1.05M | — |
| Input $/M | $4 | — |
| Output $/M | $20 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.6 Sol: 61.1 (#7)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| DeepSWE | 72.7% | — |
| FrontierCode | 47.5% | — |
| CursorBench | 41.7% | — |
| LMArena WebDev | 1619 | — |
| FrontierSWE | 32.2% | — |
| SciCode | 57.1% | — |
| WeirdML | 89.4% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1493 | — |
| MirrorCode | 20% | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 2,177 | — |

## Agentic & Tool Use

- GPT-5.6 Sol: 50.2 (#7)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| APEX-Agents | 51.4% | — |
| OSWorld 2.0 | 27.3% | — |
| τ²-bench Banking | 46.9% | — |
| PostTrainBench | 36.2% | — |
| BALROG | 60% | — |
| GBAEval | 52.6% | — |
| GDP.pdf | 30.7% | — |
| LMArena Search | 1257 | — |
| Vending-Bench 2 | 9,619 | — |

## Reasoning

- GPT-5.6 Sol: 74.7 (#6)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 161.99 | 121.18 |
| ARC-AGI-2 | 92.5% | — |
| SimpleBench | 71.7% | — |
| Kagi LLM Benchmark | 67% | — |
| NYT Connections (extended) | 93.8% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 32.3% | — |
| Chess Puzzles | 64% | — |
| EnigmaEval | 37.1% | — |
| EBR-Bench | 44.8% | — |
| LMArena Hard Prompts | 1481 | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 96% | — |
| LMCA | 59.2% | — |
| Surface Evolver Bench | 93.1% | — |
| Adversarial NLI | — | 55.8% |
| Bench to the Future 3 | 0.14 | — |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- GPT-5.6 Sol: 85.5 (#7)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.1% | — |
| FrontierMath Tier 4 | 82.9% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
| LMArena Math | 1472 | — |
| MATH Level 5 | — | 17.6% |
| FrontierMath Erdős | 0% | — |

## Knowledge

- GPT-5.6 Sol: 64.3 (#16)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 93.5% | 27.6% |
| SimpleQA Verified | 69.7% | — |
| Vectara Hallucination Rate | 12.4% | — |
| LMArena Expert | 1517 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multimodal

- GPT-5.6 Sol: 48.9 (#8)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1281 | — |
| Blueprint-Bench 2 | 33.6% | — |
| Furniture Assembly | 56.7% | — |
| LMArena Document | 1483 | — |

## Multilingual

- GPT-5.6 Sol: 55.4 (#32)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1450 | — |
| LMArena Chinese | 1523 | — |
| LMArena French | 1475 | — |
| LMArena German | 1476 | — |
| LMArena Japanese | 1475 | — |
| LMArena Korean | 1434 | — |
| LMArena Russian | 1466 | — |
| LMArena Spanish | 1449 | — |

## Instruction Following

- GPT-5.6 Sol: 77.8 (#16)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1480 | — |

## Long Context

- GPT-5.6 Sol: 45.3 (#42)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1479 | — |

## Writing & Preference

- GPT-5.6 Sol: 73.5 (#12)
- phi-3-medium 14B: —

| Benchmark | GPT-5.6 Sol | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1456 | — |
| LMArena Creative Writing | 1450 | — |
| EQ-Bench Creative Writing | 1972 | — |
| EQ-Bench 4 | 1250 | — |
| LMArena Multi-Turn | 1456 | — |

## FAQ

### Is GPT-5.6 Sol better than phi-3-medium 14B?

GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 29.1 on the Noometry Index.

### Is GPT-5.6 Sol or phi-3-medium 14B better for coding?

GPT-5.6 Sol scores higher on coding benchmarks: 61.1 versus 36.3 in the Noometry coding category.

### How many benchmarks do GPT-5.6 Sol and phi-3-medium 14B share?

2 benchmarks have published results for both models. GPT-5.6 Sol has 64 scored results on Noometry and phi-3-medium 14B has 13.