Model comparison
Amazon Nova Pro vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 31.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 2 categories and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 43.9.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Amazon Nova Pro and 14.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 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 Large 3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Mistral Large 3 | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.0 | 39.1 |
| Released | 2024-12-03 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 8K |
| Input $ / M tokens | $0.80 | $0.25 |
| Output $ / M tokens | $3.20 | $0.75 |
| Results tracked | 38 | 24 |
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 Large 3: 34.4 (#237)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1270 | 1448 |
| LMArena WebDev | — | 1230 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Mistral Large 3: —
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Mistral Large 3: 15.2 (#319)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math Mistral Large 3 leads
Amazon Nova Pro: 28.5 (#243), Mistral Large 3: 38.7 (#129)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1252 | 1414 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Mistral Large 3 leads
Amazon Nova Pro: 27.4 (#250), Mistral Large 3: 36.0 (#177)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 14.5% |
| LMArena Expert | 1211 | 1421 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Mistral Large 3 leads
Amazon Nova Pro: 25.0 (#126), Mistral Large 3: 38.2 (#66)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 980 | 1221 |
Multilingual Mistral Large 3 leads
Amazon Nova Pro: 39.7 (#223), Mistral Large 3: 52.5 (#84)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1234 | 1413 |
| LMArena Chinese | 1244 | 1447 |
| LMArena French | 1271 | 1455 |
| LMArena German | 1243 | 1437 |
| LMArena Japanese | 1200 | 1394 |
| LMArena Korean | 1203 | 1384 |
| LMArena Russian | 1240 | 1411 |
| LMArena Spanish | 1182 | 1440 |
Instruction Following Mistral Large 3 leads
Amazon Nova Pro: 64.9 (#226), Mistral Large 3: 74.0 (#108)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1403 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Mistral Large 3 leads
Amazon Nova Pro: 38.1 (#205), Mistral Large 3: 43.1 (#105)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1255 | 1413 |
Writing & Preference Mistral Large 3 leads
Amazon Nova Pro: 43.9 (#226), Mistral Large 3: 60.0 (#101)
| Benchmark | Amazon Nova Pro | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1259 | 1428 |
| LMArena Creative Writing | 1212 | 1386 |
| LMArena Multi-Turn | 1246 | 1429 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1412 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Mistral Large 3 better for coding?
They score almost the same on coding (35.1 vs 34.4); 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 Large 3 share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Mistral Large 3 has 24.