Model comparison
Amazon Nova Pro vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 31.0 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and Mistral Small in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 16.4.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 37.1% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Mistral Small | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.0 | 33.4 |
| Released | 2024-12-03 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 256K |
| Input $ / M tokens | $0.80 | $0.15 |
| Output $ / M tokens | $3.20 | $0.60 |
| Results tracked | 38 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Mistral Small: 34.0 (#247)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LiveBench Coding | 38.1% | 36.2% |
| LMArena Coding | 1270 | 1362 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Mistral Small leads
Amazon Nova Pro: 16.7 (#147), Mistral Small: 28.1 (#93)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 37.1% |
| TheAgentCompany | 1.7% | — |
Reasoning Too close to call
Amazon Nova Pro: 20.0 (#243), Mistral Small: 19.8 (#250)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 32.6% | 44.8% |
| LMArena Hard Prompts | 1246 | 1335 |
| LiveBench Data Analysis | 48.3% | 53.7% |
| LiveBench | 43.5% | 44% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 123.8 | — |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Mistral Small: 16.4 (#293)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LiveBench Math | 38% | 39.9% |
| LMArena Math | 1252 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 46.8% |
Knowledge Mistral Small leads
Amazon Nova Pro: 27.4 (#250), Mistral Small: 31.0 (#222)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 5.1% |
| LMArena Expert | 1211 | 1291 |
| MMLU | 82% | 68.7% |
| GPQA Diamond | — | 47.5% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
Multimodal Mistral Small leads
Amazon Nova Pro: 25.0 (#126), Mistral Small: 33.5 (#96)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LMArena Vision | 980 | 1142 |
Multilingual Mistral Small leads
Amazon Nova Pro: 39.7 (#223), Mistral Small: 45.5 (#169)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LMArena Non-English | 1234 | 1315 |
| LMArena Chinese | 1244 | 1340 |
| LMArena French | 1271 | 1337 |
| LMArena German | 1243 | 1340 |
| LMArena Japanese | 1200 | 1275 |
| LMArena Korean | 1203 | 1259 |
| LMArena Russian | 1240 | 1324 |
| LMArena Spanish | 1182 | 1346 |
Instruction Following Mistral Small leads
Amazon Nova Pro: 64.9 (#226), Mistral Small: 66.4 (#209)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 63.7% |
| LMArena Instruction Following | 1235 | 1310 |
| IFEval | 81.5% | — |
Long Context Mistral Small leads
Amazon Nova Pro: 38.1 (#205), Mistral Small: 40.4 (#156)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1255 | 1327 |
Writing & Preference Mistral Small leads
Amazon Nova Pro: 43.9 (#226), Mistral Small: 52.5 (#171)
| Benchmark | Amazon Nova Pro | Mistral Small |
|---|---|---|
| LMArena Text | 1259 | 1338 |
| LMArena Creative Writing | 1212 | 1305 |
| LMArena Multi-Turn | 1246 | 1344 |
| LiveBench Language | 37% | 30.5% |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Mistral Small better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 262K.
How many benchmarks do Amazon Nova Pro and Mistral Small share?
28 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Mistral Small has 39.