Model comparison
Llama 4 Maverick vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 30.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
NVIDIASummary
- They share 20 benchmarks with published results for both. Llama 4 Maverick scores higher in 1 category and Nemotron 3 Super in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Super leads 56.1 to 39.0.
- The biggest single-benchmark swing is WeirdML: 24.5% for Llama 4 Maverick and 38% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- Nemotron 3 Super accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Maverick | Nemotron 3 Super | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.6 | 39.6 |
| Released | 2025-04-05 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.19 | $0.08 |
| Output $ / M tokens | $0.65 | $0.45 |
| Results tracked | 54 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Llama 4 Maverick: 26.3 (#318), Nemotron 3 Super: 38.9 (#153)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| SciCode | 33.1% | 36% |
| WeirdML | 24.5% | 38% |
| LMArena Coding | 1302 | 1403 |
| ALE-Bench | 172.97 | 213.9 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 27.9 (#86), Nemotron 3 Super: —
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Nemotron 3 Super leads
Llama 4 Maverick: 10.1 (#337), Nemotron 3 Super: 17.9 (#274)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 8% | 15.4% |
| CritPt | 0% | 3.1% |
| LMArena Hard Prompts | 1281 | 1386 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| ARC-AGI-1 | 4.4% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Nemotron 3 Super leads
Llama 4 Maverick: 24.6 (#256), Nemotron 3 Super: 37.6 (#95)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1299 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Nemotron 3 Super leads
Llama 4 Maverick: 33.3 (#196), Nemotron 3 Super: 38.2 (#136)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1259 | 1397 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 30.9 (#100), Nemotron 3 Super: —
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1141 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Nemotron 3 Super leads
Llama 4 Maverick: 42.4 (#190), Nemotron 3 Super: 48.6 (#139)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1269 | 1356 |
| LMArena Chinese | 1277 | 1430 |
| LMArena French | 1258 | 1404 |
| LMArena German | 1291 | 1341 |
| LMArena Russian | 1286 | 1336 |
| LMArena Spanish | 1293 | 1417 |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
Instruction Following Too close to call
Llama 4 Maverick: 71.9 (#140), Nemotron 3 Super: 71.4 (#149)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1267 | 1347 |
| IFEval | 90.8% | — |
Long Context Nemotron 3 Super leads
Llama 4 Maverick: 31.4 (#274), Nemotron 3 Super: 41.5 (#134)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1280 | 1362 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Nemotron 3 Super leads
Llama 4 Maverick: 39.0 (#247), Nemotron 3 Super: 56.1 (#135)
| Benchmark | Llama 4 Maverick | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1287 | 1378 |
| LMArena Creative Writing | 1266 | 1317 |
| LMArena Multi-Turn | 1289 | 1369 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 30.6 on the Noometry Index.
Which is cheaper, Llama 4 Maverick 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; Llama 4 Maverick lists at $0.19 and $0.65.
Is Llama 4 Maverick or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 26.3 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Maverick and Nemotron 3 Super share?
20 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Nemotron 3 Super has 21.