Model comparison
Amazon Nova Micro vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.4 on the Noometry Index. Amazon Nova Micro costs 8.6× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
MiniMaxSummary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and MiniMax-M2.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 39.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 11.8% for MiniMax-M2.1.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 128K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | MiniMax-M2.1 | |
|---|---|---|
| Provider | Amazon | MiniMax |
| Noometry Index | 30.4 | 38.9 |
| Released | 2024-12-03 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | 128K | 205K |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.035 | $0.30 |
| Output $ / M tokens | $0.14 | $1.20 |
| Results tracked | 32 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Amazon Nova Micro: 30.5 (#295), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1218 | 1421 |
| LMArena WebDev | — | 1384 |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use MiniMax-M2.1 leads
Amazon Nova Micro: 22.1 (#132), MiniMax-M2.1: 27.9 (#98)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Too close to call
Amazon Nova Micro: 17.4 (#294), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| LiveBench | 29.6% | — |
Math MiniMax-M2.1 leads
Amazon Nova Micro: 26.9 (#254), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1206 | 1397 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge MiniMax-M2.1 leads
Amazon Nova Micro: 29.6 (#237), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 11.8% |
| LMArena Expert | 1184 | 1431 |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual MiniMax-M2.1 leads
Amazon Nova Micro: 36.5 (#239), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1186 | 1378 |
| LMArena Chinese | 1209 | 1430 |
| LMArena French | 1238 | 1404 |
| LMArena German | 1192 | 1381 |
| LMArena Japanese | 1154 | 1287 |
| LMArena Korean | 1150 | 1298 |
| LMArena Russian | 1185 | 1387 |
| LMArena Spanish | 1225 | 1397 |
Instruction Following MiniMax-M2.1 leads
Amazon Nova Micro: 56.3 (#272), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1400 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context MiniMax-M2.1 leads
Amazon Nova Micro: 36.5 (#229), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1205 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Amazon Nova Micro: 39.5 (#247), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Amazon Nova Micro | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1208 | 1392 |
| LMArena Creative Writing | 1172 | 1361 |
| LMArena Multi-Turn | 1178 | 1396 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.4 on the Noometry Index. Amazon Nova Micro costs 8.6× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or MiniMax-M2.1?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is Amazon Nova Micro or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 128K.
How many benchmarks do Amazon Nova Micro and MiniMax-M2.1 share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and MiniMax-M2.1 has 22.