Model comparison
Amazon Nova Experimental Chat 10 20 vs MiniMax-M2.1
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 41.5 to 38.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. Amazon Nova Experimental Chat 10 20 scores higher in 4 categories and MiniMax-M2.1 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Amazon Nova Experimental Chat 10 20 leads 27.3 to 15.8.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 | |
|---|---|---|
| Provider | Amazon | MiniMax |
| Noometry Index | 41.5 | 38.4 |
| Released | — | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Experimental Chat 10 20: 41.0 (#123), MiniMax-M2.1: 40.1 (#132)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1413 | 1421 |
| LMArena WebDev | — | 1384 |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Not comparable
Amazon Nova Experimental Chat 10 20: —, MiniMax-M2.1: 27.7 (#91)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 27.3 (#110), MiniMax-M2.1: 15.8 (#301)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1410 |
| NYT Connections (extended) | — | 11.2% |
Math Too close to call
Amazon Nova Experimental Chat 10 20: 36.2 (#121), MiniMax-M2.1: 35.6 (#142)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1425 | 1396 |
Knowledge Too close to call
Amazon Nova Experimental Chat 10 20: 37.8 (#142), MiniMax-M2.1: 37.7 (#143)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1385 | 1432 |
| Vectara Hallucination Rate | — | 11.8% |
Multilingual Too close to call
Amazon Nova Experimental Chat 10 20: 49.7 (#127), MiniMax-M2.1: 50.2 (#123)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1372 | 1378 |
| LMArena Chinese | 1405 | 1430 |
| LMArena French | 1426 | 1405 |
| LMArena German | 1391 | 1380 |
| LMArena Japanese | 1355 | 1287 |
| LMArena Korean | 1327 | 1297 |
| LMArena Russian | 1371 | 1386 |
| LMArena Spanish | 1381 | 1396 |
Instruction Following MiniMax-M2.1 leads
Amazon Nova Experimental Chat 10 20: 72.3 (#136), MiniMax-M2.1: 74.0 (#108)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1365 | 1399 |
Long Context MiniMax-M2.1 leads
Amazon Nova Experimental Chat 10 20: 41.7 (#128), MiniMax-M2.1: 43.2 (#98)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1370 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Amazon Nova Experimental Chat 10 20: 56.9 (#131), MiniMax-M2.1: 58.5 (#114)
| Benchmark | Amazon Nova Experimental Chat 10 20 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1394 | 1392 |
| LMArena Creative Writing | 1318 | 1362 |
| LMArena Multi-Turn | 1364 | 1396 |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 20 better than MiniMax-M2.1?
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 41.5 to 38.4 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 20 or MiniMax-M2.1 better for coding?
They score almost the same on coding (41.0 vs 40.1); test both on your own repository before choosing.
How many benchmarks do Amazon Nova Experimental Chat 10 20 and MiniMax-M2.1 share?
17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and MiniMax-M2.1 has 22.