Model comparison
Amazon Nova Micro vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 30.4 on the Noometry Index. Amazon Nova Micro costs 49× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Mistral AISummary
- They share 32 benchmarks with published results for both. Amazon Nova Micro scores higher in 2 categories and Mistral Large in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Large leads 67.9 to 56.3.
- The biggest single-benchmark swing is LiveBench Coding: 20.2% for Amazon Nova Micro and 47.1% for Mistral Large.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Mistral Large | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 30.4 | 31.9 |
| Released | 2024-12-03 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.035 | $2 |
| Output $ / M tokens | $0.14 | $6 |
| Results tracked | 32 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Amazon Nova Micro: 30.5 (#295), Mistral Large: 34.3 (#240)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| LiveBench Coding | 20.2% | 47.1% |
| LMArena Coding | 1218 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
Amazon Nova Micro: 22.1 (#132), Mistral Large: 28.6 (#89)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 38.4% |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), Mistral Large: 15.8 (#310)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| LiveBench Reasoning | 25.1% | 43.5% |
| LMArena Hard Prompts | 1191 | 1257 |
| LiveBench Data Analysis | 34% | 50.1% |
| LiveBench | 29.6% | 48.4% |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| DTBench | — | 65.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
Math Amazon Nova Micro leads
Amazon Nova Micro: 26.9 (#254), Mistral Large: 18.2 (#291)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| Omni-MATH | 21.4% | 28.1% |
| LiveBench Math | 34.5% | 42.5% |
| LMArena Math | 1206 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Too close to call
Amazon Nova Micro: 29.6 (#237), Mistral Large: 30.1 (#230)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| MMLU-Pro | 51.1% | 59.9% |
| Vectara Hallucination Rate | 5.5% | 4.5% |
| GPQA (HELM) | 38.3% | 43.5% |
| LMArena Expert | 1184 | 1232 |
| MMLU | 70.8% | 80% |
| GPQA Diamond | — | 51.3% |
| Confabulations | — | 21.4% |
Multilingual Mistral Large leads
Amazon Nova Micro: 36.5 (#239), Mistral Large: 40.0 (#219)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| LMArena Non-English | 1186 | 1237 |
| LMArena Chinese | 1209 | 1240 |
| LMArena French | 1238 | 1325 |
| LMArena German | 1192 | 1254 |
| LMArena Japanese | 1154 | 1188 |
| LMArena Korean | 1150 | 1202 |
| LMArena Russian | 1185 | 1257 |
| LMArena Spanish | 1225 | 1268 |
Instruction Following Mistral Large leads
Amazon Nova Micro: 56.3 (#272), Mistral Large: 67.9 (#191)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 48% | 67.9% |
| IFEval | 76% | 87.7% |
| LMArena Instruction Following | 1174 | 1249 |
Long Context Mistral Large leads
Amazon Nova Micro: 36.5 (#229), Mistral Large: 38.3 (#199)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1205 | 1261 |
Writing & Preference Mistral Large leads
Amazon Nova Micro: 39.5 (#247), Mistral Large: 40.7 (#242)
| Benchmark | Amazon Nova Micro | Mistral Large |
|---|---|---|
| LMArena Text | 1208 | 1266 |
| LMArena Creative Writing | 1172 | 1243 |
| WildBench | 74.3% | 80.1% |
| LMArena Multi-Turn | 1178 | 1260 |
| LiveBench Language | 15.8% | 39.4% |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
Frequently asked questions
Is Amazon Nova Micro better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 30.4 on the Noometry Index. Amazon Nova Micro costs 49× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Mistral Large?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Mistral Large lists at $2 and $6.
Is Amazon Nova Micro or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Mistral Large share?
32 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Mistral Large has 51.