Model comparison
Amazon Nova Micro vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.4 on the Noometry Index. Amazon Nova Micro costs 8.6× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and MiniMax-M3 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 29.6.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 128K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | MiniMax-M3 | |
|---|---|---|
| Provider | Amazon | MiniMax |
| Noometry Index | 30.4 | 43.8 |
| Released | 2024-12-03 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 128K | 1M |
| Max output | 10K | 512K |
| Input $ / M tokens | $0.035 | $0.30 |
| Output $ / M tokens | $0.14 | $1.20 |
| Results tracked | 32 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Amazon Nova Micro: 30.5 (#295), MiniMax-M3: 41.8 (#118)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1218 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Too close to call
Amazon Nova Micro: 22.1 (#132), MiniMax-M3: 22.6 (#130)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Amazon Nova Micro: 17.4 (#294), MiniMax-M3: 30.1 (#87)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1447 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |
| LiveBench | 29.6% | — |
Math MiniMax-M3 leads
Amazon Nova Micro: 26.9 (#254), MiniMax-M3: 40.0 (#95)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1206 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge MiniMax-M3 leads
Amazon Nova Micro: 29.6 (#237), MiniMax-M3: 58.4 (#35)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1184 | 1461 |
| GPQA Diamond | — | 90.9% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Amazon Nova Micro: 36.5 (#239), MiniMax-M3: 53.0 (#75)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1186 | 1420 |
| LMArena Chinese | 1209 | 1463 |
| LMArena French | 1238 | 1447 |
| LMArena German | 1192 | 1426 |
| LMArena Japanese | 1154 | 1381 |
| LMArena Korean | 1150 | 1372 |
| LMArena Russian | 1185 | 1428 |
| LMArena Spanish | 1225 | 1432 |
Instruction Following MiniMax-M3 leads
Amazon Nova Micro: 56.3 (#272), MiniMax-M3: 75.5 (#62)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1433 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context MiniMax-M3 leads
Amazon Nova Micro: 36.5 (#229), MiniMax-M3: 44.2 (#72)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1205 | 1445 |
Writing & Preference MiniMax-M3 leads
Amazon Nova Micro: 39.5 (#247), MiniMax-M3: 62.1 (#83)
| Benchmark | Amazon Nova Micro | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1208 | 1433 |
| LMArena Creative Writing | 1172 | 1404 |
| LMArena Multi-Turn | 1178 | 1442 |
| WildBench | 74.3% | — |
| EQ-Bench 4 | — | 1150 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.4 on the Noometry Index. Amazon Nova Micro costs 8.6× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or MiniMax-M3?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is Amazon Nova Micro or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 128K.
How many benchmarks do Amazon Nova Micro and MiniMax-M3 share?
17 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and MiniMax-M3 has 41.