Model comparison
Claude 3 Sonnet vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 28.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in math, where Nova Premier 1.0 leads 31.5 to 10.0.
Side by side
| Claude 3 Sonnet | Nova Premier 1.0 | |
|---|---|---|
| Provider | Anthropic | Amazon |
| Noometry Index | 28.8 | 37.7 |
| Released | 2024-02-29 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 10K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $12.50 |
| Results tracked | 30 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 3 Sonnet: 29.2 (#296), Nova Premier 1.0: —
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| LMArena Coding | 1223 | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Nova Premier 1.0 leads
Claude 3 Sonnet: 19.7 (#232), Nova Premier 1.0: 22.3 (#182)
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| LMArena Hard Prompts | 1197 | — |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |
Math Nova Premier 1.0 leads
Claude 3 Sonnet: 10.0 (#305), Nova Premier 1.0: 31.5 (#194)
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1213 | — |
| MATH Level 5 | 18.2% | — |
Knowledge Nova Premier 1.0 leads
Claude 3 Sonnet: 21.1 (#271), Nova Premier 1.0: 35.4 (#176)
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 40.6% | — |
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 24.7 (#120), Nova Premier 1.0: —
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Not comparable
Claude 3 Sonnet: 38.0 (#229), Nova Premier 1.0: —
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1188 | — |
| LMArena French | 1228 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Nova Premier 1.0 leads
Claude 3 Sonnet: 63.1 (#230), Nova Premier 1.0: 66.9 (#201)
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1200 | — |
Long Context Not comparable
Claude 3 Sonnet: 36.7 (#223), Nova Premier 1.0: —
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1211 | — |
Writing & Preference Nova Premier 1.0 leads
Claude 3 Sonnet: 42.3 (#233), Nova Premier 1.0: 51.0 (#174)
| Benchmark | Claude 3 Sonnet | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1218 | — |
| LMArena Creative Writing | 1186 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1227 | — |
Frequently asked questions
Is Claude 3 Sonnet better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 28.8 on the Noometry Index.
How many benchmarks do Claude 3 Sonnet and Nova Premier 1.0 share?
0 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Nova Premier 1.0 has 6.