Model comparison
Amazon Nova Micro vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.1 to 29.9 on the Noometry Index. Amazon Nova Micro costs 4.3× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Mistral Small in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.6 to 39.7.
- The biggest single-benchmark swing is LiveBench Data Analysis: 34% for Amazon Nova Micro and 53.7% for Mistral Small.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 256K tokens versus 128K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Mistral Small | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 29.9 | 33.1 |
| Released | 2024-12-03 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 128K | 256K |
| Max output | 10K | 256K |
| Input $ / M tokens | $0.035 | $0.15 |
| Output $ / M tokens | $0.14 | $0.60 |
| Results tracked | 32 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Amazon Nova Micro: 30.0 (#289), Mistral Small: 33.5 (#242)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LiveBench Coding | 20.2% | 36.2% |
| LMArena Coding | 1218 | 1363 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Mistral Small leads
Amazon Nova Micro: 21.9 (#125), Mistral Small: 27.9 (#87)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 37.1% |
Reasoning Mistral Small leads
Amazon Nova Micro: 16.7 (#289), Mistral Small: 19.3 (#238)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 25.1% | 44.8% |
| LMArena Hard Prompts | 1191 | 1336 |
| LiveBench Data Analysis | 34% | 53.7% |
| LiveBench | 29.6% | 44% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
Math Amazon Nova Micro leads
Amazon Nova Micro: 24.9 (#252), Mistral Small: 15.4 (#287)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LiveBench Math | 34.5% | 39.9% |
| LMArena Math | 1206 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| Omni-MATH | 21.4% | — |
| MATH Level 5 | — | 46.8% |
Knowledge Mistral Small leads
Amazon Nova Micro: 29.2 (#231), Mistral Small: 30.9 (#214)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 5.1% |
| LMArena Expert | 1184 | 1293 |
| MMLU | 70.8% | 68.7% |
| GPQA Diamond | — | 47.5% |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Mistral Small: 32.9 (#91)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Amazon Nova Micro: 36.7 (#234), Mistral Small: 45.7 (#164)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LMArena Non-English | 1186 | 1315 |
| LMArena Chinese | 1209 | 1342 |
| LMArena French | 1237 | 1337 |
| LMArena German | 1192 | 1341 |
| LMArena Japanese | 1154 | 1275 |
| LMArena Korean | 1150 | 1260 |
| LMArena Russian | 1185 | 1324 |
| LMArena Spanish | 1225 | 1346 |
Instruction Following Mistral Small leads
Amazon Nova Micro: 56.6 (#267), Mistral Small: 66.6 (#204)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 48% | 63.7% |
| LMArena Instruction Following | 1174 | 1310 |
| IFEval | 76% | — |
Long Context Mistral Small leads
Amazon Nova Micro: 36.5 (#224), Mistral Small: 40.4 (#151)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1206 | 1327 |
Writing & Preference Mistral Small leads
Amazon Nova Micro: 39.7 (#242), Mistral Small: 52.6 (#165)
| Benchmark | Amazon Nova Micro | Mistral Small |
|---|---|---|
| LMArena Text | 1208 | 1338 |
| LMArena Creative Writing | 1172 | 1304 |
| LMArena Multi-Turn | 1178 | 1344 |
| LiveBench Language | 15.8% | 30.5% |
| WildBench | 74.3% | — |
Frequently asked questions
Is Amazon Nova Micro better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.1 to 29.9 on the Noometry Index. Amazon Nova Micro costs 4.3× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Mistral Small?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is Amazon Nova Micro or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 33.5 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Mistral Small share?
27 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Mistral Small has 39.