Model comparison
Llama 3.1-70B vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 29.4 on the Noometry Index. Llama 3.1-70B costs 13× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
MetaSummary
- They share 5 benchmarks with published results for both. Llama 3.1-70B 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 31.5 to 12.7.
- The biggest single-benchmark swing is Omni-MATH: 21% for Llama 3.1-70B and 35% for Nova Premier 1.0.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 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 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-70B | Nova Premier 1.0 | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 29.4 | 37.7 |
| Released | 2024-07-23 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 10K |
| Input $ / M tokens | $0.40 | $2.50 |
| Output $ / M tokens | $0.40 | $12.50 |
| Results tracked | 35 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1-70B: 29.8 (#292), Nova Premier 1.0: —
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| LMArena Coding | 1260 | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 24.9 (#104), Nova Premier 1.0: —
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Nova Premier 1.0 leads
Llama 3.1-70B: 20.8 (#215), Nova Premier 1.0: 22.3 (#182)
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| LMArena Hard Prompts | 1241 | — |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.91 | — |
Math Nova Premier 1.0 leads
Llama 3.1-70B: 12.7 (#298), Nova Premier 1.0: 31.5 (#194)
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 21% | 35% |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| LMArena Math | 1252 | — |
| MATH Level 5 | 36.7% | — |
Knowledge Nova Premier 1.0 leads
Llama 3.1-70B: 24.1 (#264), Nova Premier 1.0: 35.4 (#176)
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 65.3% | 72.6% |
| GPQA (HELM) | 42.6% | 51.8% |
| GPQA Diamond | 44.2% | — |
| LMArena Expert | 1209 | — |
| MMLU | 80.1% | — |
Multilingual Not comparable
Llama 3.1-70B: 38.9 (#220), Nova Premier 1.0: —
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1219 | — |
| LMArena Chinese | 1215 | — |
| LMArena French | 1260 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Nova Premier 1.0 leads
Llama 3.1-70B: 65.5 (#218), Nova Premier 1.0: 66.9 (#201)
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| IFEval | 82.1% | 80.3% |
| LMArena Instruction Following | 1231 | — |
Long Context Not comparable
Llama 3.1-70B: 37.6 (#208), Nova Premier 1.0: —
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1241 | — |
Writing & Preference Nova Premier 1.0 leads
Llama 3.1-70B: 35.6 (#262), Nova Premier 1.0: 51.0 (#174)
| Benchmark | Llama 3.1-70B | Nova Premier 1.0 |
|---|---|---|
| WildBench | 75.8% | 78.8% |
| LMArena Text | 1261 | — |
| LMArena Creative Writing | 1232 | — |
| EQ-Bench Creative Writing | 784 | — |
| LMArena Multi-Turn | 1256 | — |
Frequently asked questions
Is Llama 3.1-70B better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 29.4 on the Noometry Index. Llama 3.1-70B costs 13× 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 3.1-70B or Nova Premier 1.0?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 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 3.1-70B and Nova Premier 1.0 share?
5 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Nova Premier 1.0 has 6.