Model comparison
GPT-5 Nano vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 33.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. GPT-5 Nano scores higher in 1 category and Nemotron 3 Super in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Super leads 55.9 to 39.1.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
- GPT-5 Nano accepts more context: 400K tokens versus 262K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 33.5 | 40.1 |
| Released | 2025-08-07 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.05 | $0.08 |
| Output $ / M tokens | $0.40 | $0.45 |
| Results tracked | 49 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
GPT-5 Nano: 33.6 (#254), Nemotron 3 Super: 39.4 (#158)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| WeirdML | 38.1% | 38% |
| LMArena Coding | 1351 | 1403 |
| ALE-Bench | 718.67 | 213.9 |
| SWE-bench Verified (bash only) | 34.8% | — |
| SciCode | — | 36% |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Nemotron 3 Super: —
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Nemotron 3 Super leads
GPT-5 Nano: 16.3 (#306), Nemotron 3 Super: 18.7 (#276)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1386 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| NYT Connections (extended) | — | 15.4% |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math Nemotron 3 Super leads
GPT-5 Nano: 29.4 (#241), Nemotron 3 Super: 39.6 (#101)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1317 | 1380 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Nemotron 3 Super leads
GPT-5 Nano: 35.9 (#178), Nemotron 3 Super: 38.9 (#139)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1321 | 1398 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Nemotron 3 Super: —
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Nemotron 3 Super leads
GPT-5 Nano: 45.3 (#172), Nemotron 3 Super: 48.4 (#144)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1313 | 1355 |
| LMArena Chinese | 1356 | 1432 |
| LMArena German | 1327 | 1341 |
| LMArena Russian | 1296 | 1336 |
| LMArena Spanish | 1360 | 1417 |
| LMArena French | — | 1405 |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Nemotron 3 Super: 71.2 (#154)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1306 | 1347 |
| IFEval | 93.2% | — |
Long Context Nemotron 3 Super leads
GPT-5 Nano: 31.3 (#281), Nemotron 3 Super: 41.5 (#139)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1312 | 1362 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Nemotron 3 Super leads
GPT-5 Nano: 39.1 (#249), Nemotron 3 Super: 55.9 (#140)
| Benchmark | GPT-5 Nano | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1320 | 1378 |
| LMArena Creative Writing | 1249 | 1317 |
| LMArena Multi-Turn | 1311 | 1369 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 33.5 on the Noometry Index.
Which is cheaper, GPT-5 Nano or Nemotron 3 Super?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is GPT-5 Nano or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Nano and Nemotron 3 Super share?
16 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Nemotron 3 Super has 21.