Model comparison
Amazon Nova Pro vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.1× less per token, which makes it the better buy when Mistral Medium 3.5'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 Pro scores higher in 1 category and Mistral Medium 3.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.5 to 43.9.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Amazon Nova Pro accepts more context: 300K tokens versus 262K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.0 | 40.2 |
| Released | 2024-12-03 | — |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 210K |
| Input $ / M tokens | $0.80 | $1.50 |
| Output $ / M tokens | $3.20 | $7.50 |
| Results tracked | 38 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Pro: 35.1 (#229), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1270 | 1461 |
| LMArena WebDev | — | 1264 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Mistral Medium 3.5: —
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1436 |
| Epoch Capabilities Index | 123.8 | 141.35 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| LiveBench | 43.5% | — |
Math Mistral Medium 3.5 leads
Amazon Nova Pro: 28.5 (#243), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1252 | 1431 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Mistral Medium 3.5 leads
Amazon Nova Pro: 27.4 (#250), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1211 | 1432 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Mistral Medium 3.5 leads
Amazon Nova Pro: 25.0 (#126), Mistral Medium 3.5: 38.3 (#65)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | 980 | 1223 |
Multilingual Mistral Medium 3.5 leads
Amazon Nova Pro: 39.7 (#223), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1404 |
| LMArena Chinese | 1244 | 1442 |
| LMArena French | 1271 | 1448 |
| LMArena German | 1243 | 1451 |
| LMArena Korean | 1203 | 1385 |
| LMArena Russian | 1240 | 1395 |
| LMArena Spanish | 1182 | 1409 |
| LMArena Japanese | 1200 | — |
Instruction Following Mistral Medium 3.5 leads
Amazon Nova Pro: 64.9 (#226), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1415 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Mistral Medium 3.5 leads
Amazon Nova Pro: 38.1 (#205), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1415 |
Writing & Preference Mistral Medium 3.5 leads
Amazon Nova Pro: 43.9 (#226), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | Amazon Nova Pro | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1259 | 1421 |
| LMArena Creative Writing | 1212 | 1374 |
| LMArena Multi-Turn | 1246 | 1423 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 993 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.1× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Mistral Medium 3.5?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Amazon Nova Pro or Mistral Medium 3.5 better for coding?
They score almost the same on coding (35.1 vs 36.0); test both on your own repository before choosing.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 262K.
How many benchmarks do Amazon Nova Pro and Mistral Medium 3.5 share?
18 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Mistral Medium 3.5 has 22.