Model comparison
GPT-5.6 Luna vs Nemotron 3 Super
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 40.1 on the Noometry Index. Nemotron 3 Super costs 2.6× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
NVIDIASummary
- They share 20 benchmarks with published results for both. GPT-5.6 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-5.6 Luna leads 77.7 to 39.6.
- The biggest single-benchmark swing is NYT Connections (extended): 69.4% for GPT-5.6 Luna and 15.4% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.20 / $1.20 for GPT-5.6 Luna.
- GPT-5.6 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-5.6 Luna | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 54.6 | 40.1 |
| Released | 2026-07-09 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.20 | $0.08 |
| Output $ / M tokens | $1.20 | $0.45 |
| Results tracked | 52 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), Nemotron 3 Super: 39.4 (#158)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| SciCode | 53.6% | 36% |
| WeirdML | 60.9% | 38% |
| LMArena Coding | 1466 | 1403 |
| ALE-Bench | 1,667 | 213.9 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), Nemotron 3 Super: —
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), Nemotron 3 Super: 18.7 (#276)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 69.4% | 15.4% |
| CritPt | 20.6% | 3.1% |
| LMArena Hard Prompts | 1451 | 1386 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| ARC-AGI-1 | 88% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.39 | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Nemotron 3 Super: 39.6 (#101)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1458 | 1380 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Nemotron 3 Super: 38.9 (#139)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1478 | 1398 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), Nemotron 3 Super: —
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 52.8 (#78), Nemotron 3 Super: 48.4 (#144)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1417 | 1355 |
| LMArena Chinese | 1470 | 1432 |
| LMArena French | 1456 | 1405 |
| LMArena German | 1454 | 1341 |
| LMArena Russian | 1428 | 1336 |
| LMArena Spanish | 1448 | 1417 |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1415 | — |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), Nemotron 3 Super: 71.2 (#154)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1437 | 1347 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), Nemotron 3 Super: 41.5 (#139)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1436 | 1362 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Nemotron 3 Super: 55.9 (#140)
| Benchmark | GPT-5.6 Luna | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1431 | 1378 |
| LMArena Creative Writing | 1396 | 1317 |
| LMArena Multi-Turn | 1434 | 1369 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Nemotron 3 Super?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 40.1 on the Noometry Index. Nemotron 3 Super costs 2.6× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 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-5.6 Luna lists at $0.20 and $1.20.
Is GPT-5.6 Luna or Nemotron 3 Super better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-5.6 Luna and Nemotron 3 Super share?
20 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Nemotron 3 Super has 21.