Model comparison
GPT-6 Luna vs Phi 3 Mini 128k Instruct
GPT-6 Luna is the stronger model overall, scoring 45.1 to 29.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
MicrosoftSummary
- They share 13 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Phi 3 Mini 128k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-6 Luna leads 58.4 to 27.3.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Phi 3 Mini 128k Instruct | |
|---|---|---|
| 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 | 19 |
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 Mini 128k Instruct: 28.3 (#307)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1448 | 1040 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1583 | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 31.7 (#68), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1028 |
| NYT Connections (extended) | 68.7% | — |
Math GPT-6 Luna leads
GPT-6 Luna: 35.6 (#140), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1396 | 1089 |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 40.1 (#110), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1458 | 984 |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), Phi 3 Mini 128k Instruct: —
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 51.0 (#111), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1390 | 1000 |
| LMArena Chinese | 1425 | 1016 |
| LMArena Russian | 1392 | 1004 |
| LMArena Spanish | 1416 | 1058 |
| LMArena French | — | 1038 |
| LMArena German | — | 1006 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
Instruction Following GPT-6 Luna leads
GPT-6 Luna: 74.7 (#85), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1414 | 1023 |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.3 (#95), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1417 | 996 |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.4 (#115), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | GPT-6 Luna | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1392 | 1050 |
| LMArena Creative Writing | 1357 | 1024 |
| LMArena Multi-Turn | 1400 | 989 |
Frequently asked questions
Is GPT-6 Luna better than Phi 3 Mini 128k Instruct?
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 Mini 128k Instruct better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 28.3 in the Noometry coding category.
How many benchmarks do GPT-6 Luna and Phi 3 Mini 128k Instruct share?
13 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.