# Amazon Nova Experimental Chat 10 20 vs Mistral Small 3

> Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 41.5 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Amazon Nova Experimental Chat 10 20 scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Experimental Chat 10 20 leads 56.9 to 32.4.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 41.5 | 30.9 |
| Rank | 122 | 268 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Experimental Chat 10 20: 41.0 (#123)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1413 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Reasoning

- Amazon Nova Experimental Chat 10 20: 27.3 (#110)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.06 |

## Math

- Amazon Nova Experimental Chat 10 20: 36.2 (#121)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1425 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |

## Knowledge

- Amazon Nova Experimental Chat 10 20: 37.8 (#142)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1385 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |

## Multilingual

- Amazon Nova Experimental Chat 10 20: 49.7 (#127)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1372 | 1198 |
| LMArena Chinese | 1405 | 1204 |
| LMArena French | 1426 | 1202 |
| LMArena German | 1391 | 1211 |
| LMArena Japanese | 1355 | 1111 |
| LMArena Korean | 1327 | 1188 |
| LMArena Russian | 1371 | 1216 |
| LMArena Spanish | 1381 | — |

## Instruction Following

- Amazon Nova Experimental Chat 10 20: 72.3 (#136)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1365 | 1214 |

## Long Context

- Amazon Nova Experimental Chat 10 20: 41.7 (#128)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1370 | 1246 |

## Writing & Preference

- Amazon Nova Experimental Chat 10 20: 56.9 (#131)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1394 | 1234 |
| LMArena Creative Writing | 1318 | 1195 |
| LMArena Multi-Turn | 1364 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Amazon Nova Experimental Chat 10 20 better than Mistral Small 3?

Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 41.5 to 30.9 on the Noometry Index.

### Is Amazon Nova Experimental Chat 10 20 or Mistral Small 3 better for coding?

Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.0 versus 36.0 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 10 20 and Mistral Small 3 share?

16 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Mistral Small 3 has 24.