Model comparison
GPT-6 Luna vs Nemotron 3 Super
GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
NVIDIASummary
- They share 19 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Nemotron 3 Super in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 39.6.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 15.4% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.10 / $0.50 for GPT-6 Luna.
- GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 53.3 | 40.1 |
| Released | 2026-09-22 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $0.08 |
| Output $ / M tokens | $0.50 | $0.45 |
| Results tracked | 42 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 55.5 (#25), Nemotron 3 Super: 39.4 (#158)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| SciCode | 54.6% | 36% |
| LMArena Coding | 1439 | 1403 |
| ALE-Bench | 1,577 | 213.9 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1581 | — |
| WeirdML | — | 38% |
Agentic & Tool Use Not comparable
GPT-6 Luna: 33.3 (#54), Nemotron 3 Super: —
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| APEX-Agents | 44.3% | — |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), Nemotron 3 Super: 18.7 (#276)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 68.7% | 15.4% |
| CritPt | 19.4% | 3.1% |
| LMArena Hard Prompts | 1411 | 1386 |
| ARC-AGI-2 | 59.3% | — |
| ARC-AGI-1 | 86.7% | — |
| Chess Puzzles | 31% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 90.1% | — |
| LMCA | 44.5% | — |
| Epoch Capabilities Index | 156.28 | — |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Nemotron 3 Super: 39.6 (#101)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1416 | 1380 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 64% | — |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), Nemotron 3 Super: 38.9 (#139)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1444 | 1398 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
Multimodal Not comparable
GPT-6 Luna: 42.4 (#30), Nemotron 3 Super: —
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1217 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 50.5 (#117), Nemotron 3 Super: 48.4 (#144)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1386 | 1355 |
| LMArena Chinese | 1433 | 1432 |
| LMArena French | 1420 | 1405 |
| LMArena German | 1369 | 1341 |
| LMArena Russian | 1394 | 1336 |
| LMArena Spanish | 1393 | 1417 |
| LMArena Japanese | 1369 | — |
| LMArena Korean | 1360 | — |
Instruction Following GPT-6 Luna leads
GPT-6 Luna: 74.3 (#99), Nemotron 3 Super: 71.2 (#154)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1409 | 1347 |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.0 (#111), Nemotron 3 Super: 41.5 (#139)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1409 | 1362 |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.3 (#119), Nemotron 3 Super: 55.9 (#140)
| Benchmark | GPT-6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1391 | 1378 |
| LMArena Creative Writing | 1363 | 1317 |
| LMArena Multi-Turn | 1396 | 1369 |
Frequently asked questions
Is GPT-6 Luna better than Nemotron 3 Super?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.1 on the Noometry Index.
Which is cheaper, GPT-6 Luna or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; GPT-6 Luna lists at $0.10 and $0.50.
Is GPT-6 Luna or Nemotron 3 Super better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Luna and Nemotron 3 Super share?
19 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Nemotron 3 Super has 21.