Model comparison
Llama 4 Maverick vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 30.9 on the Noometry Index. Llama 4 Maverick costs 3.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Meta
NVIDIASummary
- They share 25 benchmarks with published results for both. Llama 4 Maverick scores higher in 1 category and Nemotron 3 Ultra in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 38.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 20.6% for Llama 4 Maverick and 86.7% for Nemotron 3 Ultra.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Maverick | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.9 | 42.5 |
| Released | 2025-04-05 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.19 | $0.50 |
| Output $ / M tokens | $0.65 | $2.20 |
| Results tracked | 54 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Llama 4 Maverick: 26.6 (#324), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 33.1% | 40.3% |
| WeirdML | 24.5% | 43.5% |
| LMArena Coding | 1302 | 1468 |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Llama 4 Maverick leads
Llama 4 Maverick: 28.2 (#91), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Nemotron 3 Ultra leads
Llama 4 Maverick: 10.1 (#342), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| LMArena Hard Prompts | 1281 | 1452 |
| DTBench | 61.9% | 90.1% |
| LMCA | 15.9% | 36.9% |
| Epoch Capabilities Index | 132.2 | 146.17 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| Chess Puzzles | — | 12% |
| EnigmaEval | 0.6% | — |
| Mystery Game Puzzles | — | 20% |
| ForecastBench | 57.5 | — |
Math Nemotron 3 Ultra leads
Llama 4 Maverick: 26.0 (#262), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 86.7% |
| LMArena Math | 1299 | 1457 |
| ProofBench | — | 2% |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Nemotron 3 Ultra leads
Llama 4 Maverick: 33.4 (#204), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 67% | 85.4% |
| LMArena Expert | 1259 | 1472 |
| 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: 31.6 (#105), Nemotron 3 Ultra: —
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Nemotron 3 Ultra leads
Llama 4 Maverick: 42.2 (#195), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1269 | 1427 |
| LMArena Chinese | 1277 | 1497 |
| LMArena French | 1259 | 1472 |
| LMArena German | 1291 | 1471 |
| LMArena Korean | 1203 | 1386 |
| LMArena Russian | 1286 | 1417 |
| LMArena Spanish | 1293 | 1454 |
| LMArena Japanese | 1207 | — |
Instruction Following Nemotron 3 Ultra leads
Llama 4 Maverick: 71.7 (#146), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1267 | 1418 |
| IFEval | 90.8% | — |
Long Context Nemotron 3 Ultra leads
Llama 4 Maverick: 31.4 (#279), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1280 | 1437 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Nemotron 3 Ultra leads
Llama 4 Maverick: 38.8 (#252), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Llama 4 Maverick | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1287 | 1445 |
| LMArena Creative Writing | 1267 | 1398 |
| EQ-Bench Creative Writing | 860 | 1692 |
| LMArena Multi-Turn | 1289 | 1411 |
| Short-Story Creative Writing | 62% | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 30.9 on the Noometry Index. Llama 4 Maverick costs 3.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or Nemotron 3 Ultra?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is Llama 4 Maverick or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Maverick and Nemotron 3 Ultra share?
25 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Nemotron 3 Ultra has 30.