Model comparison
Amazon Nova Pro vs Chatgpt 4o Latest 20250326
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 31.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Chatgpt 4o Latest 20250326 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Chatgpt 4o Latest 20250326 leads 62.6 to 43.9.
- The biggest single-benchmark swing is Confabulations: 30.1% for Amazon Nova Pro and 16.6% for Chatgpt 4o Latest 20250326.
Side by side
| Amazon Nova Pro | Chatgpt 4o Latest 20250326 | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 43.8 |
| Released | 2024-12-03 | — |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 35.1 (#229), Chatgpt 4o Latest 20250326: 41.6 (#122)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Coding | 1270 | 1413 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Chatgpt 4o Latest 20250326: —
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 20.0 (#243), Chatgpt 4o Latest 20250326: 33.8 (#71)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1424 |
| Kagi LLM Benchmark | — | 75% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 28.5 (#243), Chatgpt 4o Latest 20250326: 38.6 (#134)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Math | 1252 | 1407 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 27.4 (#250), Chatgpt 4o Latest 20250326: 39.2 (#137)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| Confabulations | 30.1% | 16.6% |
| LMArena Expert | 1211 | 1401 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 25.0 (#126), Chatgpt 4o Latest 20250326: 39.6 (#58)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Vision | 980 | 1243 |
Multilingual Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 39.7 (#223), Chatgpt 4o Latest 20250326: 52.9 (#76)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Non-English | 1234 | 1419 |
| LMArena Chinese | 1244 | 1457 |
| LMArena French | 1271 | 1446 |
| LMArena German | 1243 | 1423 |
| LMArena Japanese | 1200 | 1405 |
| LMArena Korean | 1203 | 1396 |
| LMArena Russian | 1240 | 1429 |
| LMArena Spanish | 1182 | 1434 |
Instruction Following Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 64.9 (#226), Chatgpt 4o Latest 20250326: 74.0 (#107)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1403 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 38.1 (#205), Chatgpt 4o Latest 20250326: 43.1 (#107)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Longer Query | 1255 | 1413 |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Amazon Nova Pro: 43.9 (#226), Chatgpt 4o Latest 20250326: 62.6 (#72)
| Benchmark | Amazon Nova Pro | Chatgpt 4o Latest 20250326 |
|---|---|---|
| LMArena Text | 1259 | 1429 |
| LMArena Creative Writing | 1212 | 1405 |
| LMArena Multi-Turn | 1246 | 1454 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1501 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Chatgpt 4o Latest 20250326?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Chatgpt 4o Latest 20250326 better for coding?
Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.6 versus 35.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Chatgpt 4o Latest 20250326 share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Chatgpt 4o Latest 20250326 has 21.