Model comparison
GPT-6 Luna vs Nova Premier 1.0
GPT-6 Luna is the stronger model overall, scoring 45.1 to 37.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in reasoning, where GPT-6 Luna leads 31.7 to 22.3.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-6 Luna | Nova Premier 1.0 | |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 45.1 | 37.7 |
| Released | 2026-09-22 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 10K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.50 | $12.50 |
| Results tracked | 18 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-6 Luna: 54.7 (#24), Nova Premier 1.0: —
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1583 | — |
| LMArena Coding | 1448 | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 31.7 (#68), Nova Premier 1.0: 22.3 (#182)
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| NYT Connections (extended) | 68.7% | — |
| LMArena Hard Prompts | 1415 | — |
Math GPT-6 Luna leads
GPT-6 Luna: 35.6 (#140), Nova Premier 1.0: 31.5 (#194)
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | — | 35% |
| LMArena Math | 1396 | — |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 40.1 (#110), Nova Premier 1.0: 35.4 (#176)
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1458 | — |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), Nova Premier 1.0: —
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual Not comparable
GPT-6 Luna: 51.0 (#111), Nova Premier 1.0: —
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1390 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1416 | — |
Instruction Following GPT-6 Luna leads
GPT-6 Luna: 74.7 (#85), Nova Premier 1.0: 66.9 (#201)
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
GPT-6 Luna: 43.3 (#95), Nova Premier 1.0: —
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1417 | — |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.4 (#115), Nova Premier 1.0: 51.0 (#174)
| Benchmark | GPT-6 Luna | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1357 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1400 | — |
Frequently asked questions
Is GPT-6 Luna better than Nova Premier 1.0?
GPT-6 Luna is the stronger model overall, scoring 45.1 to 37.7 on the Noometry Index.
Which is cheaper, GPT-6 Luna or Nova Premier 1.0?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1M.
How many benchmarks do GPT-6 Luna and Nova Premier 1.0 share?
0 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Nova Premier 1.0 has 6.