Model comparison
Amazon Nova Pro vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.0 on the Noometry Index. Amazon Nova Pro costs 3.2× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Gemini 3.1 Pro Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 20.0.
- The biggest single-benchmark swing is Humanity's Last Exam: 4.4% for Amazon Nova Pro and 46.4% for Gemini 3.1 Pro Preview.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 31.0 | 56.7 |
| Released | 2024-12-03 | 2026-02-19 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $12 |
| Results tracked | 38 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 35.1 (#229), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Coding | 1270 | 1484 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| LiveBench Coding | 38.1% | — |
| MirrorCode | — | 8.9% |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
Agentic & Tool Use Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 16.7 (#147), Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 20.0 (#243), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1485 |
| Epoch Capabilities Index | 123.8 | 154.77 |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.1% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 53.8% |
| ForecastBench | — | 59 |
| LiveBench | 43.5% | — |
Math Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 28.5 (#243), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Math | 1252 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 27.4 (#250), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| Humanity's Last Exam | 4.4% | 46.4% |
| Vectara Hallucination Rate | 5.1% | 10.4% |
| LMArena Expert | 1211 | 1485 |
| GPQA Diamond | — | 94.4% |
| SimpleQA Verified | — | 73.5% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 25.0 (#126), Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 980 | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 39.7 (#223), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1234 | 1477 |
| LMArena Chinese | 1244 | 1529 |
| LMArena French | 1271 | 1487 |
| LMArena German | 1243 | 1491 |
| LMArena Japanese | 1200 | 1493 |
| LMArena Korean | 1203 | 1455 |
| LMArena Russian | 1240 | 1498 |
| LMArena Spanish | 1182 | 1479 |
Instruction Following Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 64.9 (#226), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1235 | 1466 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 38.1 (#205), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1255 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Gemini 3.1 Pro Preview leads
Amazon Nova Pro: 43.9 (#226), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | Amazon Nova Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1259 | 1481 |
| LMArena Creative Writing | 1212 | 1482 |
| LMArena Multi-Turn | 1246 | 1488 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1491 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1142 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.0 on the Noometry Index. Amazon Nova Pro costs 3.2× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Gemini 3.1 Pro Preview?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Amazon Nova Pro or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and Gemini 3.1 Pro Preview share?
21 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemini 3.1 Pro Preview has 71.