Model comparison
Amazon Nova Pro vs GPT-5.6 Terra
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 30.5 on the Noometry Index. Amazon Nova Pro costs 3.2× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5.6 Terra in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.5 to 26.4.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-5.6 Terra | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.5 | 59.1 |
| Released | 2024-12-03 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $12 |
| Results tracked | 38 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
Amazon Nova Pro: 34.6 (#224), GPT-5.6 Terra: 57.1 (#16)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Coding | 1270 | 1484 |
| DeepSWE | — | 69.6% |
| FrontierCode | — | 41.3% |
| CursorBench | — | 41.3% |
| LMArena WebDev | — | 1520 |
| SciCode | — | 55% |
| WeirdML | — | 78.3% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,951 |
Agentic & Tool Use GPT-5.6 Terra leads
Amazon Nova Pro: 16.6 (#139), GPT-5.6 Terra: 40.2 (#23)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | — | 58.2% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 53.2% |
| GDP.pdf | — | 24.7% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.6 Terra leads
Amazon Nova Pro: 19.2 (#240), GPT-5.6 Terra: 60.6 (#19)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1467 |
| Epoch Capabilities Index | 123.75 | 159.31 |
| ARC-AGI-2 | — | 83.9% |
| SimpleBench | — | 48.9% |
| Kagi LLM Benchmark | — | 51.3% |
| NYT Connections (extended) | — | 78.4% |
| ARC-AGI-1 | — | 96.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 54% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 35% |
| DTBench | — | 93.3% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 55% |
| Surface Evolver Bench | — | 83.8% |
| LiveBench | 43.5% | — |
Math GPT-5.6 Terra leads
Amazon Nova Pro: 26.4 (#240), GPT-5.6 Terra: 81.5 (#10)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Math | 1252 | 1463 |
| FrontierMath (Tiers 1-3) | — | 86% |
| FrontierMath Tier 4 | — | 70.7% |
| OTIS Mock AIME 2024-2025 | — | 99.7% |
| ProofBench | — | 74% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge GPT-5.6 Terra leads
Amazon Nova Pro: 27.1 (#246), GPT-5.6 Terra: 61.3 (#27)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Expert | 1211 | 1492 |
| GPQA Diamond | — | 93.3% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 43.2% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal GPT-5.6 Terra leads
Amazon Nova Pro: 24.5 (#121), GPT-5.6 Terra: 47.5 (#10)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | 980 | 1271 |
| Blueprint-Bench 2 | — | 30.8% |
| Furniture Assembly | — | 54.2% |
| LMArena Document | — | 1472 |
Multilingual GPT-5.6 Terra leads
Amazon Nova Pro: 39.9 (#218), GPT-5.6 Terra: 54.5 (#42)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1234 | 1439 |
| LMArena Chinese | 1244 | 1514 |
| LMArena French | 1270 | 1476 |
| LMArena German | 1243 | 1462 |
| LMArena Japanese | 1200 | 1446 |
| LMArena Korean | 1203 | 1420 |
| LMArena Russian | 1240 | 1450 |
| LMArena Spanish | 1182 | 1455 |
Instruction Following GPT-5.6 Terra leads
Amazon Nova Pro: 65.1 (#221), GPT-5.6 Terra: 76.6 (#38)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1235 | 1453 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context GPT-5.6 Terra leads
Amazon Nova Pro: 38.1 (#199), GPT-5.6 Terra: 44.4 (#64)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1255 | 1452 |
Writing & Preference GPT-5.6 Terra leads
Amazon Nova Pro: 44.1 (#221), GPT-5.6 Terra: 70.4 (#21)
| Benchmark | Amazon Nova Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1259 | 1446 |
| LMArena Creative Writing | 1212 | 1411 |
| LMArena Multi-Turn | 1245 | 1451 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1855 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1234 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-5.6 Terra?
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 30.5 on the Noometry Index. Amazon Nova Pro costs 3.2× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or GPT-5.6 Terra?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is Amazon Nova Pro or GPT-5.6 Terra better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 34.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-5.6 Terra share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5.6 Terra has 52.