Model comparison
Amazon Nova Pro vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.9× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-6 Sol in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 28.5.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-6 Sol | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 61.8 |
| Released | 2024-12-03 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $10 |
| Results tracked | 38 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Amazon Nova Pro: 35.1 (#229), GPT-6 Sol: 60.1 (#11)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1270 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 2,462 |
Agentic & Tool Use GPT-6 Sol leads
Amazon Nova Pro: 16.7 (#147), GPT-6 Sol: 37.2 (#36)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Amazon Nova Pro: 20.0 (#243), GPT-6 Sol: 74.0 (#9)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1418 |
| Epoch Capabilities Index | 123.8 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 97.3% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 59.1% |
| LiveBench | 43.5% | — |
Math GPT-6 Sol leads
Amazon Nova Pro: 28.5 (#243), GPT-6 Sol: 87.2 (#7)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1252 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge GPT-6 Sol leads
Amazon Nova Pro: 27.4 (#250), GPT-6 Sol: 64.8 (#15)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 6.5% |
| LMArena Expert | 1211 | 1439 |
| GPQA Diamond | — | 94.3% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal GPT-6 Sol leads
Amazon Nova Pro: 25.0 (#126), GPT-6 Sol: 47.6 (#10)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 980 | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Amazon Nova Pro: 39.7 (#223), GPT-6 Sol: 50.5 (#118)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1234 | 1385 |
| LMArena Chinese | 1244 | 1405 |
| LMArena French | 1271 | 1410 |
| LMArena German | 1243 | 1390 |
| LMArena Japanese | 1200 | 1385 |
| LMArena Korean | 1203 | 1341 |
| LMArena Russian | 1240 | 1401 |
| LMArena Spanish | 1182 | 1384 |
Instruction Following GPT-6 Sol leads
Amazon Nova Pro: 64.9 (#226), GPT-6 Sol: 74.5 (#94)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1235 | 1412 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context GPT-6 Sol leads
Amazon Nova Pro: 38.1 (#205), GPT-6 Sol: 43.1 (#108)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1255 | 1411 |
Writing & Preference GPT-6 Sol leads
Amazon Nova Pro: 43.9 (#226), GPT-6 Sol: 71.9 (#18)
| Benchmark | Amazon Nova Pro | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1259 | 1395 |
| LMArena Creative Writing | 1212 | 1378 |
| LMArena Multi-Turn | 1246 | 1412 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 2125 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.9× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or GPT-6 Sol?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is Amazon Nova Pro or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-6 Sol share?
20 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-6 Sol has 45.