Model comparison
Amazon Nova Pro vs Grok 3
Grok 3 is the stronger model overall, scoring 39.9 to 31.0 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Grok 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 27.4.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 46.4% for Grok 3.
Side by side
| Amazon Nova Pro | Grok 3 | |
|---|---|---|
| Provider | Amazon | xAI |
| Noometry Index | 31.0 | 39.9 |
| Released | 2024-12-03 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Amazon Nova Pro: 35.1 (#229), Grok 3: 41.9 (#115)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| LMArena Coding | 1270 | 1432 |
| Aider Polyglot | — | 53.3% |
| WeirdML | — | 37.2% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Grok 3 leads
Amazon Nova Pro: 16.7 (#147), Grok 3: 30.5 (#76)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 29.5% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Grok 3: 13.7 (#333)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1434 |
| Epoch Capabilities Index | 123.8 | 138.33 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 5.5% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| LiveBench | 43.5% | — |
Math Grok 3 leads
Amazon Nova Pro: 28.5 (#243), Grok 3: 38.0 (#145)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| Omni-MATH | 24.2% | 46.4% |
| LMArena Math | 1252 | 1391 |
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
Amazon Nova Pro: 27.4 (#250), Grok 3: 46.2 (#82)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| MMLU-Pro | 67.3% | 78.8% |
| Confabulations | 30.1% | 14.2% |
| Vectara Hallucination Rate | 5.1% | 5.8% |
| GPQA (HELM) | 44.6% | 65% |
| LMArena Expert | 1211 | 1421 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 4.4% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Grok 3: —
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Grok 3 leads
Amazon Nova Pro: 39.7 (#223), Grok 3: 52.3 (#87)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| LMArena Non-English | 1234 | 1410 |
| LMArena Chinese | 1244 | 1448 |
| LMArena French | 1271 | 1460 |
| LMArena German | 1243 | 1431 |
| LMArena Japanese | 1200 | 1387 |
| LMArena Korean | 1203 | 1373 |
| LMArena Russian | 1240 | 1416 |
| LMArena Spanish | 1182 | 1417 |
Instruction Following Grok 3 leads
Amazon Nova Pro: 64.9 (#226), Grok 3: 75.0 (#73)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| IFEval | 81.5% | 88.4% |
| LMArena Instruction Following | 1235 | 1409 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), Grok 3: 38.7 (#192)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1255 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Grok 3 leads
Amazon Nova Pro: 43.9 (#226), Grok 3: 55.8 (#141)
| Benchmark | Amazon Nova Pro | Grok 3 |
|---|---|---|
| LMArena Text | 1259 | 1426 |
| LMArena Creative Writing | 1212 | 1414 |
| Short-Story Creative Writing | 60.5% | 76.4% |
| WildBench | 77.7% | 84.9% |
| LMArena Multi-Turn | 1246 | 1425 |
| EQ-Bench Creative Writing | — | 1186 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.9 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 35.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Grok 3 share?
26 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Grok 3 has 40.