Model comparison
Amazon Nova Lite vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 31.9 on the Noometry Index. Amazon Nova Lite costs 2.5× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Amazon Nova Lite scores higher in 1 category and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Lite leads 27.8 to 16.4.
- The biggest single-benchmark swing is LiveBench Data Analysis: 37.2% for Amazon Nova Lite and 53.7% for Mistral Small.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Amazon Nova Lite accepts more context: 300K tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Mistral Small | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.9 | 33.4 |
| Released | 2024-12-03 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 256K |
| Input $ / M tokens | $0.06 | $0.15 |
| Output $ / M tokens | $0.24 | $0.60 |
| Results tracked | 34 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Amazon Nova Lite: 32.5 (#270), Mistral Small: 34.0 (#247)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LiveBench Coding | 27.5% | 36.2% |
| LMArena Coding | 1239 | 1362 |
| ALE-Bench | 236.25 | 497.62 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, Mistral Small: 28.1 (#93)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Too close to call
Amazon Nova Lite: 19.3 (#260), Mistral Small: 19.8 (#250)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 36.7% | 44.8% |
| LMArena Hard Prompts | 1220 | 1335 |
| LiveBench Data Analysis | 37.2% | 53.7% |
| LiveBench | 36.4% | 44% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), Mistral Small: 16.4 (#293)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LiveBench Math | 36.7% | 39.9% |
| LMArena Math | 1227 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| Omni-MATH | 23.3% | — |
| MATH Level 5 | — | 46.8% |
Knowledge Mistral Small leads
Amazon Nova Lite: 26.3 (#259), Mistral Small: 31.0 (#222)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 6.1% | 5.1% |
| LMArena Expert | 1201 | 1291 |
| MMLU | 77% | 68.7% |
| GPQA Diamond | — | 47.5% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| GPQA (HELM) | 39.7% | — |
Multimodal Mistral Small leads
Amazon Nova Lite: 25.5 (#123), Mistral Small: 33.5 (#96)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LMArena Vision | 990 | 1142 |
Multilingual Mistral Small leads
Amazon Nova Lite: 38.0 (#232), Mistral Small: 45.5 (#169)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LMArena Non-English | 1208 | 1315 |
| LMArena Chinese | 1225 | 1340 |
| LMArena French | 1237 | 1337 |
| LMArena German | 1229 | 1340 |
| LMArena Japanese | 1153 | 1275 |
| LMArena Korean | 1153 | 1259 |
| LMArena Russian | 1216 | 1324 |
| LMArena Spanish | 1226 | 1346 |
Instruction Following Mistral Small leads
Amazon Nova Lite: 59.3 (#255), Mistral Small: 66.4 (#209)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 54.1% | 63.7% |
| LMArena Instruction Following | 1205 | 1310 |
| IFEval | 77.6% | — |
Long Context Mistral Small leads
Amazon Nova Lite: 37.4 (#217), Mistral Small: 40.4 (#156)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1234 | 1327 |
Writing & Preference Mistral Small leads
Amazon Nova Lite: 42.1 (#237), Mistral Small: 52.5 (#171)
| Benchmark | Amazon Nova Lite | Mistral Small |
|---|---|---|
| LMArena Text | 1229 | 1338 |
| LMArena Creative Writing | 1197 | 1305 |
| LMArena Multi-Turn | 1199 | 1344 |
| LiveBench Language | 25.9% | 30.5% |
| WildBench | 75% | — |
Frequently asked questions
Is Amazon Nova Lite better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 31.9 on the Noometry Index. Amazon Nova Lite costs 2.5× 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 Lite or Mistral Small?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is Amazon Nova Lite or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 32.5 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Lite does, with 300K tokens against 262K.
How many benchmarks do Amazon Nova Lite and Mistral Small share?
28 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Mistral Small has 39.