Nova Pro 1.0 vs GPT-4
Updated October 21, 2026. 32 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Nova Pro 1.0 has the edge where output tokens cost 18.8x less, and where the context window is larger, 300K against 8K tokens.
- Shared results
- 32
- Nova Pro 1.0 only
- 10
- GPT-4 only
- 13
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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 Pro 1.0
Nova Pro 1.0 leads, 7.0 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Nova Pro 1.0 has a Design Arena: websites result, 796.
Directional only
Long documents
Listed context window
Nova Pro 1.0
Nova Pro 1.0 takes 300K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nova Pro 1.0
Nova Pro 1.0 $0.0024, GPT-4 $0.060 per turn.
List prices
At a glance
- Coding index
- Nova Pro 1.0 not benchmarked, GPT-4 not benchmarked.
- Widest category
- Knowledge, 13.1 points apart on average over 6 shared benchmarks.
- Widest single gap
- LMArena Text: Korean: Nova Pro 1.0 1203 against GPT-4 1087, 19.3 points apart on a 0 to 100 scale.
- Output price
- Nova Pro 1.0 $3.20 against GPT-4 $60.00 per million output tokens, 18.8x apart.
- Context window
- Nova Pro 1.0 takes 300K 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 Pro 1.0 | Bars | GPT-4 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 5 | 1 | ||
| General | 16 | 1 | ||
| All shared boards | 30 | 2 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Nova Pro 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) | 23.3% | Not measured | Only Nova Pro 1.0 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.1% | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: coding | 1270 | 1209 | Nova Pro 1.0 |
| LMArena Text: software and IT | 1271 | 1195 | Nova Pro 1.0 |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.0 | 6.7 | Nova Pro 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 Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 14.0% | Not measured | Only Nova Pro 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 index40
| Benchmark | Nova Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 49.9% | 34.9% | Nova Pro 1.0 |
| Humanity's Last Exam (Artificial Analysis run) | 3.2% | Not measured | Only Nova Pro 1.0 measured |
| BIG-Bench Hard | Not measured | 75.1% | Only GPT-4 measured |
| LMArena Text: hard prompts | 1246 | 1200 | Nova Pro 1.0 |
| LMArena Text: expert | 1211 | 1149 | Nova Pro 1.0 |
| LMArena Text: hard prompts in English | 1259 | 1209 | Nova Pro 1.0 |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Nova Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| AA Math Index | 7.0 | Not measured | Only Nova Pro 1.0 measured |
| AIME 2025 (Artificial Analysis run) | 7.0% | Not measured | Only Nova Pro 1.0 measured |
| GSM8K | Not measured | 92.0% | Only GPT-4 measured |
| LMArena Text: math | 1252 | 1230 | Nova Pro 1.0 |
| LMArena Text: mathematical work | 1261 | 1228 | Nova Pro 1.0 |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Nova Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 69.1% | 56.2% | Nova Pro 1.0 |
| MMLU | 82.0% | 86.4% | GPT-4 |
| AI2 Reasoning Challenge | Not measured | 96.3% | Only GPT-4 measured |
| LMArena Text: science | 1255 | 1177 | Nova Pro 1.0 |
| LMArena Text: medicine and healthcare | 1260 | 1145 | Nova Pro 1.0 |
| LMArena Text: legal and government | 1281 | 1191 | Nova Pro 1.0 |
| LMArena Text: business and finance | 1229 | 1145 | Nova Pro 1.0 |
| 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 Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| Design Arena: websites | 796 | Not measured | Only Nova Pro 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 index161
| Benchmark | Nova Pro 1.0 | GPT-4 | Leader |
|---|---|---|---|
| IFBench | 38.1% | 33.2% | Nova Pro 1.0 |
| Long context reasoning (AA-LCR) | 21.0% | Not measured | Only Nova Pro 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 | 1259 | 1206 | Nova Pro 1.0 |
| LMArena Text: instruction following | 1235 | 1201 | Nova Pro 1.0 |
| LMArena Text: creative writing | 1212 | 1191 | Nova Pro 1.0 |
| LMArena Vision | 980 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: English | 1276 | 1220 | Nova Pro 1.0 |
| LMArena Text: non-English | 1233 | 1194 | Nova Pro 1.0 |
| LMArena Text: Chinese | 1244 | 1184 | Nova Pro 1.0 |
| LMArena Text: German | 1243 | 1198 | Nova Pro 1.0 |
| LMArena Text: Japanese | 1200 | 1137 | Nova Pro 1.0 |
| LMArena Text: Korean | 1203 | 1087 | Nova Pro 1.0 |
| LMArena Text: French | 1271 | 1220 | Nova Pro 1.0 |
| LMArena Text: Spanish | 1182 | 1197 | GPT-4 |
| LMArena Text: Russian | 1240 | 1195 | Nova Pro 1.0 |
| LMArena Text: Polish | Not measured | 1265 | Only GPT-4 measured |
| LMArena Text: multi-turn | 1246 | 1206 | Nova Pro 1.0 |
| LMArena Text: longer queries | 1255 | 1190 | Nova Pro 1.0 |
| LMArena Text: writing and language | 1247 | 1219 | Nova Pro 1.0 |
| LMArena Text: entertainment and media | 1210 | 1184 | Nova Pro 1.0 |
| LMArena Vision: English | 987 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Pro 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 Pro 1.0 costs less
Repository review
50K input + 3K output tokens
Nova Pro 1.0 costs less
Agent loop
200K input + 10K output tokens
Nova Pro 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 Pro 1.0 | OpenAI GPT-4 |
|---|---|---|
| Maker | Amazon | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | December 5, 2024 | May 28, 2023 |
| Context window | 300K | 8K |
| Input $/Mtok | $0.80 | $30.00 |
| Output $/Mtok | $3.20 | $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 Pro 1.0 better than GPT-4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Nova Pro 1.0 has the edge where output tokens cost 18.8x less, and where the context window is larger, 300K against 8K tokens.
Which is cheaper, Nova Pro 1.0 or GPT-4?
Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 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 Pro 1.0 or GPT-4?
Nova Pro 1.0, with 300K tokens against 8K.
How many benchmarks is the Nova Pro 1.0 vs GPT-4 comparison based on?
32 benchmarks have a result for both models as of October 21, 2026. Nova Pro 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.