Model comparison
Llama 4 Maverick vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 16× 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 Maverick scores higher in 1 category and Nova Premier 1.0 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Nova Premier 1.0 leads 23.0 to 10.1.
- The biggest single-benchmark swing is GPQA (HELM): 65% for Llama 4 Maverick and 51.8% for Nova Premier 1.0.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 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 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Nova Premier 1.0 | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 30.9 | 38.3 |
| Released | 2025-04-05 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 10K |
| Input $ / M tokens | $0.19 | $2.50 |
| Output $ / M tokens | $0.65 | $12.50 |
| Results tracked | 54 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 4 Maverick: 26.6 (#324), Nova Premier 1.0: —
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| LMArena Coding | 1302 | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Nova Premier 1.0: —
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Nova Premier 1.0 leads
Llama 4 Maverick: 10.1 (#342), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 55.9% | 44.8% |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| LMArena Hard Prompts | 1281 | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Nova Premier 1.0 leads
Llama 4 Maverick: 26.0 (#262), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 42.2% | 35% |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| LMArena Math | 1299 | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Nova Premier 1.0 leads
Llama 4 Maverick: 33.4 (#204), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 81% | 72.6% |
| GPQA (HELM) | 65% | 51.8% |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| LMArena Expert | 1259 | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Nova Premier 1.0: —
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Not comparable
Llama 4 Maverick: 42.2 (#195), Nova Premier 1.0: —
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1277 | — |
| LMArena French | 1259 | — |
| LMArena German | 1291 | — |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1286 | — |
| LMArena Spanish | 1293 | — |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| IFEval | 90.8% | 80.3% |
| LMArena Instruction Following | 1267 | — |
Long Context Not comparable
Llama 4 Maverick: 31.4 (#279), Nova Premier 1.0: —
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| Fiction.LiveBench | 46.2% | — |
| LMArena Longer Query | 1280 | — |
Writing & Preference Nova Premier 1.0 leads
Llama 4 Maverick: 38.8 (#252), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Llama 4 Maverick | Nova Premier 1.0 |
|---|---|---|
| WildBench | 80% | 78.8% |
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1267 | — |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| LMArena Multi-Turn | 1289 | — |
Frequently asked questions
Is Llama 4 Maverick better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 16× 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 Maverick or Nova Premier 1.0?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 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 Maverick and Nova Premier 1.0 share?
6 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Nova Premier 1.0 has 6.