Model comparison
GPT-4 vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in math, where Nova Premier 1.0 leads 33.8 to 10.8.
- Nova Premier 1.0 is cheaper at $2.50 / $12.50 per million input/output tokens, against $30 / $60 for GPT-4.
- Nova Premier 1.0 accepts more context: 1M tokens versus 8K.
Side by side
| GPT-4 | Nova Premier 1.0 | |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 29.1 | 38.3 |
| Released | 2023-03-14 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 1M |
| Max output | 8K | 10K |
| Input $ / M tokens | $30 | $2.50 |
| Output $ / M tokens | $60 | $12.50 |
| Results tracked | 38 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-4: 31.6 (#283), Nova Premier 1.0: —
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| LMArena Coding | 1254 | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Nova Premier 1.0: —
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Nova Premier 1.0 leads
GPT-4: 17.8 (#289), Nova Premier 1.0: 23.0 (#185)
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1241 | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Nova Premier 1.0 leads
GPT-4: 10.8 (#309), Nova Premier 1.0: 33.8 (#199)
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Nova Premier 1.0 leads
GPT-4: 18.4 (#282), Nova Premier 1.0: 35.8 (#180)
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 35.7% | — |
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1211 | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Not comparable
GPT-4: 40.6 (#215), Nova Premier 1.0: —
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1246 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Nova Premier 1.0 leads
GPT-4: 65.3 (#222), Nova Premier 1.0: 66.8 (#204)
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
GPT-4: 37.7 (#212), Nova Premier 1.0: —
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1244 | — |
Writing & Preference Nova Premier 1.0 leads
GPT-4: 34.9 (#268), Nova Premier 1.0: 51.0 (#178)
| Benchmark | GPT-4 | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1263 | — |
| LMArena Creative Writing | 1244 | — |
| EQ-Bench Creative Writing | 752 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1257 | — |
Frequently asked questions
Is GPT-4 better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or Nova Premier 1.0?
Nova Premier 1.0 is cheaper. It lists at $2.50 per million input tokens and $12.50 per million output tokens; GPT-4 lists at $30 and $60.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 8K.
How many benchmarks do GPT-4 and Nova Premier 1.0 share?
0 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Nova Premier 1.0 has 6.