Model comparison
GPT-6 Luna vs phi-3-medium 14B
GPT-6 Luna is the stronger model overall, scoring 45.1 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where GPT-6 Luna leads 40.1 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | phi-3-medium 14B | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 45.1 | 29.1 |
| Released | 2026-09-22 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 18 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 54.7 (#24), phi-3-medium 14B: 36.3 (#198)
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1583 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1448 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
GPT-6 Luna: 31.7 (#68), phi-3-medium 14B: —
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| NYT Connections (extended) | 68.7% | — |
| LMArena Hard Prompts | 1415 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math GPT-6 Luna leads
GPT-6 Luna: 35.6 (#140), phi-3-medium 14B: 25.2 (#249)
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1396 | — |
| MATH Level 5 | — | 17.6% |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 40.1 (#110), phi-3-medium 14B: 9.1 (#301)
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1458 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), phi-3-medium 14B: —
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual Not comparable
GPT-6 Luna: 51.0 (#111), phi-3-medium 14B: —
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1390 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1416 | — |
Instruction Following Not comparable
GPT-6 Luna: 74.7 (#85), phi-3-medium 14B: —
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
GPT-6 Luna: 43.3 (#95), phi-3-medium 14B: —
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1417 | — |
Writing & Preference Not comparable
GPT-6 Luna: 58.4 (#115), phi-3-medium 14B: —
| Benchmark | GPT-6 Luna | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1357 | — |
| LMArena Multi-Turn | 1400 | — |
Frequently asked questions
Is GPT-6 Luna better than phi-3-medium 14B?
GPT-6 Luna is the stronger model overall, scoring 45.1 to 29.1 on the Noometry Index.
Is GPT-6 Luna or phi-3-medium 14B better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 36.3 in the Noometry coding category.
How many benchmarks do GPT-6 Luna and phi-3-medium 14B share?
0 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and phi-3-medium 14B has 13.