Model comparison
Amazon Nova Pro vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.0× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Amazon Nova Pro scores higher in 2 categories and Magistral Medium in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Amazon Nova Pro leads 20.0 to 8.6.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Amazon Nova Pro accepts more context: 300K tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Magistral Medium | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.0 | 35.2 |
| Released | 2024-12-03 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $5 |
| Results tracked | 38 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Amazon Nova Pro: 35.1 (#229), Magistral Medium: 39.1 (#161)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Coding | 1270 | 1319 |
| SciCode | — | 39.2% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Magistral Medium: —
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Magistral Medium: 8.6 (#348)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math Magistral Medium leads
Amazon Nova Pro: 28.5 (#243), Magistral Medium: 35.1 (#189)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Math | 1252 | 1250 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Magistral Medium leads
Amazon Nova Pro: 27.4 (#250), Magistral Medium: 33.5 (#202)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Expert | 1211 | 1223 |
| 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 Not comparable
Amazon Nova Pro: 25.0 (#126), Magistral Medium: —
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Too close to call
Amazon Nova Pro: 39.7 (#223), Magistral Medium: 39.6 (#224)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1234 | 1232 |
| LMArena Chinese | 1244 | 1227 |
| LMArena French | 1271 | 1267 |
| LMArena German | 1243 | 1248 |
| LMArena Japanese | 1200 | 1175 |
| LMArena Korean | 1203 | 1125 |
| LMArena Russian | 1240 | 1224 |
| LMArena Spanish | 1182 | 1271 |
Instruction Following Magistral Medium leads
Amazon Nova Pro: 64.9 (#226), Magistral Medium: 66.0 (#211)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1235 | 1254 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Magistral Medium leads
Amazon Nova Pro: 38.1 (#205), Magistral Medium: 39.3 (#183)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1255 | 1295 |
Writing & Preference Magistral Medium leads
Amazon Nova Pro: 43.9 (#226), Magistral Medium: 46.3 (#219)
| Benchmark | Amazon Nova Pro | Magistral Medium |
|---|---|---|
| LMArena Text | 1259 | 1255 |
| LMArena Creative Writing | 1212 | 1245 |
| LMArena Multi-Turn | 1246 | 1275 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.0× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Magistral Medium?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Magistral Medium lists at $2 and $5.
Is Amazon Nova Pro or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.1 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 Magistral Medium share?
17 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Magistral Medium has 22.