Model comparison
Llama 4 Scout vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 27.7 on the Noometry Index. Llama 4 Scout costs 33× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
MetaSummary
- They share 6 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Nova Premier 1.0 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova Premier 1.0 leads 33.8 to 19.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 36.9% for Llama 4 Scout and 44.8% for Nova Premier 1.0.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Nova Premier 1.0 | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 27.7 | 38.3 |
| Released | 2025-04-05 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 10K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.30 | $12.50 |
| Results tracked | 43 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 4 Scout: 20.2 (#339), Nova Premier 1.0: —
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| LMArena Coding | 1286 | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Nova Premier 1.0: —
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Nova Premier 1.0 leads
Llama 4 Scout: 9.1 (#345), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 44.8% |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1266 | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Nova Premier 1.0 leads
Llama 4 Scout: 19.6 (#286), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 37.3% | 35% |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| LMArena Math | 1287 | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Nova Premier 1.0 leads
Llama 4 Scout: 31.9 (#217), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 74.2% | 72.6% |
| GPQA (HELM) | 50.7% | 51.8% |
| GPQA Diamond | 51.8% | — |
| Vectara Hallucination Rate | 7.7% | — |
| LMArena Expert | 1235 | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Nova Premier 1.0: —
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Not comparable
Llama 4 Scout: 41.0 (#212), Nova Premier 1.0: —
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1252 | — |
| LMArena Chinese | 1255 | — |
| LMArena French | 1282 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1206 | — |
| LMArena Korean | 1207 | — |
| LMArena Russian | 1263 | — |
| LMArena Spanish | 1278 | — |
Instruction Following Nova Premier 1.0 leads
Llama 4 Scout: 65.8 (#217), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| IFEval | 81.8% | 80.3% |
| LMArena Instruction Following | 1248 | — |
Long Context Not comparable
Llama 4 Scout: 27.5 (#294), Nova Premier 1.0: —
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| Fiction.LiveBench | 36% | — |
| LMArena Longer Query | 1265 | — |
Writing & Preference Nova Premier 1.0 leads
Llama 4 Scout: 37.0 (#261), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Llama 4 Scout | Nova Premier 1.0 |
|---|---|---|
| WildBench | 78% | 78.8% |
| LMArena Text | 1279 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 783 | — |
| LMArena Multi-Turn | 1280 | — |
Frequently asked questions
Is Llama 4 Scout better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 27.7 on the Noometry Index. Llama 4 Scout costs 33× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Nova Premier 1.0?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 128K.
How many benchmarks do Llama 4 Scout and Nova Premier 1.0 share?
6 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Nova Premier 1.0 has 6.