Model comparison
Amazon Nova Micro vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.0 to 29.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.7 to 56.6.
- The biggest single-benchmark swing is GPQA (HELM): 38.3% for Amazon Nova Micro and 67.5% for Grok-3 mini.
Side by side
| Amazon Nova Micro | Grok-3 mini | |
|---|---|---|
| Provider | Amazon | xAI |
| Noometry Index | 29.9 | 41.0 |
| Released | 2024-12-03 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Amazon Nova Micro: 30.0 (#289), Grok-3 mini: 40.4 (#126)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1218 | 1380 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 21.9 (#125), Grok-3 mini: —
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 16.7 (#289), Grok-3 mini: 13.8 (#323)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1374 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| Epoch Capabilities Index | — | 140.35 |
| LiveBench | 29.6% | — |
Math Grok-3 mini leads
Amazon Nova Micro: 24.9 (#252), Grok-3 mini: 40.3 (#78)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| Omni-MATH | 21.4% | 31.8% |
| LMArena Math | 1206 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Amazon Nova Micro: 29.2 (#231), Grok-3 mini: 46.3 (#75)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| MMLU-Pro | 51.1% | 79.9% |
| GPQA (HELM) | 38.3% | 67.5% |
| LMArena Expert | 1184 | 1395 |
| GPQA Diamond | — | 76.3% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | 70.8% | — |
Multilingual Grok-3 mini leads
Amazon Nova Micro: 36.7 (#234), Grok-3 mini: 48.3 (#141)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1186 | 1352 |
| LMArena Chinese | 1209 | 1387 |
| LMArena French | 1237 | 1357 |
| LMArena German | 1192 | 1350 |
| LMArena Japanese | 1154 | 1343 |
| LMArena Korean | 1150 | 1336 |
| LMArena Russian | 1185 | 1352 |
| LMArena Spanish | 1225 | 1379 |
Instruction Following Grok-3 mini leads
Amazon Nova Micro: 56.6 (#267), Grok-3 mini: 78.7 (#8)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| IFEval | 76% | 95.1% |
| LMArena Instruction Following | 1174 | 1356 |
| LiveBench Instruction Following | 48% | — |
Long Context Grok-3 mini leads
Amazon Nova Micro: 36.5 (#224), Grok-3 mini: 41.0 (#142)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1206 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Amazon Nova Micro: 39.7 (#242), Grok-3 mini: 52.7 (#163)
| Benchmark | Amazon Nova Micro | Grok-3 mini |
|---|---|---|
| LMArena Text | 1208 | 1370 |
| LMArena Creative Writing | 1172 | 1342 |
| WildBench | 74.3% | 65.1% |
| LMArena Multi-Turn | 1178 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.0 to 29.9 on the Noometry Index.
Is Amazon Nova Micro or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.4 versus 30.0 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and Grok-3 mini share?
22 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Grok-3 mini has 35.