Model comparison
Amazon Nova Micro vs MiniMax-M2.7
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 30.4 on the Noometry Index. Amazon Nova Micro costs 8.6× less per token, which makes it the better buy when MiniMax-M2.7'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-M2.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 39.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 12.9% for MiniMax-M2.7.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- MiniMax-M2.7 accepts more context: 205K tokens versus 128K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | MiniMax-M2.7 | |
|---|---|---|
| Provider | Amazon | MiniMax |
| Noometry Index | 30.4 | 37.7 |
| Released | 2024-12-03 | 2026-03-18 |
| 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 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Amazon Nova Micro: 30.5 (#295), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1218 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use MiniMax-M2.7 leads
Amazon Nova Micro: 22.1 (#132), MiniMax-M2.7: 25.1 (#111)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning MiniMax-M2.7 leads
Amazon Nova Micro: 17.4 (#294), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1422 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| Epoch Capabilities Index | — | 145.85 |
| LiveBench | 29.6% | — |
Math Too close to call
Amazon Nova Micro: 26.9 (#254), MiniMax-M2.7: 25.9 (#263)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1206 | 1420 |
| ProofBench | — | 3% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge MiniMax-M2.7 leads
Amazon Nova Micro: 29.6 (#237), MiniMax-M2.7: 37.7 (#152)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 12.9% |
| LMArena Expert | 1184 | 1444 |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual MiniMax-M2.7 leads
Amazon Nova Micro: 36.5 (#239), MiniMax-M2.7: 50.3 (#123)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1186 | 1382 |
| LMArena Chinese | 1209 | 1441 |
| LMArena French | 1238 | 1421 |
| LMArena German | 1192 | 1398 |
| LMArena Japanese | 1154 | 1262 |
| LMArena Korean | 1150 | 1313 |
| LMArena Russian | 1185 | 1383 |
| LMArena Spanish | 1225 | 1403 |
Instruction Following MiniMax-M2.7 leads
Amazon Nova Micro: 56.3 (#272), MiniMax-M2.7: 74.1 (#103)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1405 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context MiniMax-M2.7 leads
Amazon Nova Micro: 36.5 (#229), MiniMax-M2.7: 43.3 (#99)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1205 | 1419 |
Writing & Preference MiniMax-M2.7 leads
Amazon Nova Micro: 39.5 (#247), MiniMax-M2.7: 58.9 (#112)
| Benchmark | Amazon Nova Micro | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1208 | 1405 |
| LMArena Creative Writing | 1172 | 1354 |
| LMArena Multi-Turn | 1178 | 1412 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than MiniMax-M2.7?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 30.4 on the Noometry Index. Amazon Nova Micro costs 8.6× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or MiniMax-M2.7?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.
Is Amazon Nova Micro or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.7 does, with 205K tokens against 128K.
How many benchmarks do Amazon Nova Micro and MiniMax-M2.7 share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and MiniMax-M2.7 has 30.