Model comparison
Amazon Nova Pro vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 31.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 27.4.
- The biggest single-benchmark swing is GPQA (HELM): 44.6% for Amazon Nova Pro and 67.5% for Grok-3 mini.
Side by side
| Amazon Nova Pro | Grok-3 mini | |
|---|---|---|
| Provider | Amazon | xAI |
| Noometry Index | 31.0 | 41.2 |
| 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 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Amazon Nova Pro: 35.1 (#229), Grok-3 mini: 40.8 (#131)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1270 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Grok-3 mini: —
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Grok-3 mini: 13.6 (#334)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1375 |
| Epoch Capabilities Index | 123.8 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| LiveBench | 43.5% | — |
Math Grok-3 mini leads
Amazon Nova Pro: 28.5 (#243), Grok-3 mini: 42.1 (#85)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| Omni-MATH | 24.2% | 31.8% |
| LMArena Math | 1252 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Amazon Nova Pro: 27.4 (#250), Grok-3 mini: 46.4 (#81)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| MMLU-Pro | 67.3% | 79.9% |
| Confabulations | 30.1% | 10.8% |
| GPQA (HELM) | 44.6% | 67.5% |
| LMArena Expert | 1211 | 1395 |
| GPQA Diamond | — | 76.3% |
| Humanity's Last Exam | 4.4% | — |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Grok-3 mini: —
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Grok-3 mini leads
Amazon Nova Pro: 39.7 (#223), Grok-3 mini: 48.1 (#145)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1234 | 1352 |
| LMArena Chinese | 1244 | 1387 |
| LMArena French | 1271 | 1357 |
| LMArena German | 1243 | 1349 |
| LMArena Japanese | 1200 | 1342 |
| LMArena Korean | 1203 | 1335 |
| LMArena Russian | 1240 | 1353 |
| LMArena Spanish | 1182 | 1381 |
Instruction Following Grok-3 mini leads
Amazon Nova Pro: 64.9 (#226), Grok-3 mini: 78.5 (#9)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| IFEval | 81.5% | 95.1% |
| LMArena Instruction Following | 1235 | 1357 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Grok-3 mini leads
Amazon Nova Pro: 38.1 (#205), Grok-3 mini: 41.0 (#147)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1255 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Amazon Nova Pro: 43.9 (#226), Grok-3 mini: 52.5 (#169)
| Benchmark | Amazon Nova Pro | Grok-3 mini |
|---|---|---|
| LMArena Text | 1259 | 1370 |
| LMArena Creative Writing | 1212 | 1342 |
| Short-Story Creative Writing | 60.5% | 73.5% |
| WildBench | 77.7% | 65.1% |
| LMArena Multi-Turn | 1246 | 1355 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 35.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Grok-3 mini share?
25 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Grok-3 mini has 35.