Model comparison
Amazon Nova Micro vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.4 on the Noometry Index. Amazon Nova Micro costs 6.1× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 39.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 14.5% for Mistral Large 3.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Mistral Large 3 | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 30.4 | 39.1 |
| Released | 2024-12-03 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 10K | 8K |
| Input $ / M tokens | $0.035 | $0.25 |
| Output $ / M tokens | $0.14 | $0.75 |
| Results tracked | 32 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Amazon Nova Micro: 30.5 (#295), Mistral Large 3: 34.4 (#237)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1218 | 1448 |
| LMArena WebDev | — | 1230 |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 22.1 (#132), Mistral Large 3: —
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), Mistral Large 3: 15.2 (#319)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| LiveBench | 29.6% | — |
Math Mistral Large 3 leads
Amazon Nova Micro: 26.9 (#254), Mistral Large 3: 38.7 (#129)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1206 | 1414 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Mistral Large 3 leads
Amazon Nova Micro: 29.6 (#237), Mistral Large 3: 36.0 (#177)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 14.5% |
| LMArena Expert | 1184 | 1421 |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Amazon Nova Micro: 36.5 (#239), Mistral Large 3: 52.5 (#84)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1186 | 1413 |
| LMArena Chinese | 1209 | 1447 |
| LMArena French | 1238 | 1455 |
| LMArena German | 1192 | 1437 |
| LMArena Japanese | 1154 | 1394 |
| LMArena Korean | 1150 | 1384 |
| LMArena Russian | 1185 | 1411 |
| LMArena Spanish | 1225 | 1440 |
Instruction Following Mistral Large 3 leads
Amazon Nova Micro: 56.3 (#272), Mistral Large 3: 74.0 (#108)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1403 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Mistral Large 3 leads
Amazon Nova Micro: 36.5 (#229), Mistral Large 3: 43.1 (#105)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1205 | 1413 |
Writing & Preference Mistral Large 3 leads
Amazon Nova Micro: 39.5 (#247), Mistral Large 3: 60.0 (#101)
| Benchmark | Amazon Nova Micro | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1208 | 1428 |
| LMArena Creative Writing | 1172 | 1386 |
| LMArena Multi-Turn | 1178 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.4 on the Noometry Index. Amazon Nova Micro costs 6.1× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Mistral Large 3?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Amazon Nova Micro or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Mistral Large 3 share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Mistral Large 3 has 24.