Model comparison
Llama 3.1 Nemotron Ultra 253b v1 vs Llama 4 Scout
Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 27.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
NVIDIA
MetaSummary
- They share 11 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 7 categories and Llama 4 Scout in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Llama 3.1 Nemotron Ultra 253b v1 leads 38.4 to 20.2.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 10% for Llama 3.1 Nemotron Ultra 253b v1 and 28.1% for Llama 4 Scout.
Side by side
| Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout | |
|---|---|---|
| Provider | NVIDIA | Meta |
| Noometry Index | 36.7 | 27.7 |
| Released | — | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 11 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177), Llama 4 Scout: 20.2 (#339)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1312 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use Llama 4 Scout leads
Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149), Llama 4 Scout: 24.6 (#119)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10% | 28.1% |
Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134), Llama 4 Scout: 9.1 (#345)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1316 | 1266 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| Epoch Capabilities Index | — | 129.64 |
| ForecastBench | — | 57.5 |
Math Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152), Llama 4 Scout: 19.6 (#286)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Math | 1360 | 1287 |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Not comparable
Llama 3.1 Nemotron Ultra 253b v1: —, Llama 4 Scout: 31.9 (#217)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1235 |
Multimodal Not comparable
Llama 3.1 Nemotron Ultra 253b v1: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187), Llama 4 Scout: 41.0 (#212)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1282 | 1252 |
| LMArena Russian | 1284 | 1263 |
| LMArena Chinese | — | 1255 |
| LMArena French | — | 1282 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
| LMArena Spanish | — | 1278 |
Instruction Following Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178), Llama 4 Scout: 65.8 (#217)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1308 | 1248 |
| IFEval | — | 81.8% |
Long Context Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177), Llama 4 Scout: 27.5 (#294)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1299 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175), Llama 4 Scout: 37.0 (#261)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1320 | 1279 |
| LMArena Creative Writing | 1314 | 1249 |
| LMArena Multi-Turn | 1317 | 1280 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
Frequently asked questions
Is Llama 3.1 Nemotron Ultra 253b v1 better than Llama 4 Scout?
Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 27.7 on the Noometry Index.
Is Llama 3.1 Nemotron Ultra 253b v1 or Llama 4 Scout better for coding?
Llama 3.1 Nemotron Ultra 253b v1 scores higher on coding benchmarks: 38.4 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Llama 4 Scout share?
11 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Llama 4 Scout has 43.