Nova Premier 1.0 vs GPT-4
Nova Premier 1.0 leads GPT-4 on the Artificial Analysis Intelligence Index, 9.2 to 6.7, and Nova Premier 1.0 costs 4.8x less per output token ($12.50 vs $60.00 per million). Updated October 21, 2026; 4 benchmarks have a result for both.
Nova Premier 1.0 or GPT-4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Nova Premier 1.0 for output tokens 4.8x cheaper ($12.50 vs $60.00 per million) and a larger context window (1M against 8K tokens).
- Shared results
- 4
- Nova Premier 1.0 only
- 9
- GPT-4 only
- 41
- Like-for-like categories
- 4 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Nova Premier 1.0
Nova Premier 1.0 leads, 9.2 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Nova Premier 1.0 has a Design Arena: websites result, 835.
Directional only
Long documents
Listed context window
Nova Premier 1.0
Nova Premier 1.0 takes 1M tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nova Premier 1.0
Nova Premier 1.0 $0.0088, GPT-4 $0.060 per turn.
List prices
At a glance
- Coding index
- Nova Premier 1.0 not benchmarked, GPT-4 not benchmarked.
- Widest category
- Reasoning, 22.0 points apart on average over 1 shared benchmark.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): Nova Premier 1.0 56.9% against GPT-4 34.9%, 22.0 points apart on a 0 to 100 scale.
- Output price
- Nova Premier 1.0 $12.50 against GPT-4 $60.00 per million output tokens, 4.8x apart.
- Context window
- Nova Premier 1.0 takes 1M tokens, GPT-4 8K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Nova Premier 1.0 | Bars | GPT-4 | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 0 | ||
| Knowledge | 1 | 0 | ||
| General | 1 | 0 | ||
| All shared boards | 4 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index9 boards, none shared
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 22.4% | Only GPT-4 measured |
| SWE-bench Lite | Not measured | 39.7% | Only GPT-4 measured |
| SWE-bench (full test set) | Not measured | 12.5% | Only GPT-4 measured |
| AA Coding Index | Not measured | 13.1 | Only GPT-4 measured |
| LiveCodeBench (Artificial Analysis run) | 31.7% | Not measured | Only Nova Premier 1.0 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | Not measured | Only Nova Premier 1.0 measured |
| ALE-Bench | 147.4 | Not measured | Only Nova Premier 1.0 measured |
| LMArena Text: coding | Not measured | 1209 | Only GPT-4 measured |
| LMArena Text: software and IT | Not measured | 1195 | Only GPT-4 measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.2 | 6.7 | Nova Premier 1.0 |
| Epoch Capabilities Index | Not measured | 125.7 | Only GPT-4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 38.3% | Not measured | Only Nova Premier 1.0 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 56.9% | 34.9% | Nova Premier 1.0 |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | Not measured | Only Nova Premier 1.0 measured |
| BIG-Bench Hard | Not measured | 75.1% | Only GPT-4 measured |
| LMArena Text: hard prompts | Not measured | 1200 | Only GPT-4 measured |
| LMArena Text: expert | Not measured | 1149 | Only GPT-4 measured |
| LMArena Text: hard prompts in English | Not measured | 1209 | Only GPT-4 measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| AA Math Index | 17.3 | Not measured | Only Nova Premier 1.0 measured |
| AIME 2025 (Artificial Analysis run) | 17.3% | Not measured | Only Nova Premier 1.0 measured |
| GSM8K | Not measured | 92.0% | Only GPT-4 measured |
| LMArena Text: math | Not measured | 1230 | Only GPT-4 measured |
| LMArena Text: mathematical work | Not measured | 1228 | Only GPT-4 measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 73.3% | 56.2% | Nova Premier 1.0 |
| MMLU | Not measured | 86.4% | Only GPT-4 measured |
| AI2 Reasoning Challenge | Not measured | 96.3% | Only GPT-4 measured |
| LMArena Text: science | Not measured | 1177 | Only GPT-4 measured |
| LMArena Text: medicine and healthcare | Not measured | 1145 | Only GPT-4 measured |
| LMArena Text: legal and government | Not measured | 1191 | Only GPT-4 measured |
| LMArena Text: business and finance | Not measured | 1145 | Only GPT-4 measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| Design Arena: websites | 835 | Not measured | Only Nova Premier 1.0 measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| IFBench | 36.2% | 33.2% | Nova Premier 1.0 |
| Long context reasoning (AA-LCR) | 34.3% | Not measured | Only Nova Premier 1.0 measured |
| DTBench | Not measured | 62.7% | Only GPT-4 measured |
| LMCA | Not measured | 17.1% | Only GPT-4 measured |
| HellaSwag | Not measured | 95.3% | Only GPT-4 measured |
| WinoGrande | Not measured | 87.5% | Only GPT-4 measured |
| LMArena Text | Not measured | 1206 | Only GPT-4 measured |
| LMArena Text: instruction following | Not measured | 1201 | Only GPT-4 measured |
| LMArena Text: creative writing | Not measured | 1191 | Only GPT-4 measured |
| LMArena Text: English | Not measured | 1220 | Only GPT-4 measured |
| LMArena Text: non-English | Not measured | 1194 | Only GPT-4 measured |
| LMArena Text: Chinese | Not measured | 1184 | Only GPT-4 measured |
| LMArena Text: German | Not measured | 1198 | Only GPT-4 measured |
| LMArena Text: Japanese | Not measured | 1137 | Only GPT-4 measured |
| LMArena Text: Korean | Not measured | 1087 | Only GPT-4 measured |
| LMArena Text: French | Not measured | 1220 | Only GPT-4 measured |
| LMArena Text: Spanish | Not measured | 1197 | Only GPT-4 measured |
| LMArena Text: Russian | Not measured | 1195 | Only GPT-4 measured |
| LMArena Text: Polish | Not measured | 1265 | Only GPT-4 measured |
| LMArena Text: multi-turn | Not measured | 1206 | Only GPT-4 measured |
| LMArena Text: longer queries | Not measured | 1190 | Only GPT-4 measured |
| LMArena Text: writing and language | Not measured | 1219 | Only GPT-4 measured |
| LMArena Text: entertainment and media | Not measured | 1184 | Only GPT-4 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Premier 1.0 | GPT-4 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Nova Premier 1.0 costs less
Repository review
50K input + 3K output tokens
Nova Premier 1.0 costs less
Agent loop
200K input + 10K output tokens
Nova Premier 1.0 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Amazon Nova Premier 1.0 | OpenAI GPT-4 |
|---|---|---|
| Maker | Amazon | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 31, 2025 | May 28, 2023 |
| Context window | 1M | 8K |
| Input $/Mtok | $2.50 | $30.00 |
| Output $/Mtok | $12.50 | $60.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova Premier 1.0 better than GPT-4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova Premier 1.0 for output tokens 4.8x cheaper ($12.50 vs $60.00 per million) and a larger context window (1M against 8K tokens).
Which is cheaper, Nova Premier 1.0 or GPT-4?
Nova Premier 1.0 costs $2.50 per million input tokens and $12.50 per million output tokens; GPT-4 costs $30.00 and $60.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Premier 1.0 or GPT-4?
Nova Premier 1.0, with 1M tokens against 8K.
How many benchmarks is the Nova Premier 1.0 vs GPT-4 comparison based on?
4 benchmarks have a result for both models as of October 21, 2026. Nova Premier 1.0's coding index rests on 0 independent benchmarks and GPT-4's on 0. Where only one model has a result, the page says so instead of naming a winner.