Model comparison
Amazon Nova Lite vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 31.9 on the Noometry Index. Amazon Nova Lite costs 29× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Amazon Nova Lite scores higher in 1 category and Mistral Medium in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 42.1.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 6.1% for Amazon Nova Lite and 22.7% for Mistral Medium.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Amazon Nova Lite accepts more context: 300K tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Mistral Medium | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.9 | 36.3 |
| Released | 2024-12-03 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 262K |
| Input $ / M tokens | $0.06 | $1.50 |
| Output $ / M tokens | $0.24 | $7.50 |
| Results tracked | 34 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Amazon Nova Lite: 32.5 (#270), Mistral Medium: 34.2 (#243)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Coding | 1239 | 1434 |
| ALE-Bench | 236.25 | 763.98 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| LiveBench Coding | 27.5% | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, Mistral Medium: 28.3 (#90)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Amazon Nova Lite: 19.3 (#260), Mistral Medium: 24.0 (#167)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 75.5% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| LiveBench | 36.4% | — |
Math Too close to call
Amazon Nova Lite: 27.8 (#247), Mistral Medium: 28.1 (#245)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Math | 1227 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Amazon Nova Lite leads
Amazon Nova Lite: 26.3 (#259), Mistral Medium: 25.0 (#265)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| Humanity's Last Exam | 3.6% | 4.5% |
| Vectara Hallucination Rate | 6.1% | 22.7% |
| LMArena Expert | 1201 | 1408 |
| GPQA Diamond | — | 59.5% |
| MMLU-Pro | 60% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |
Multimodal Mistral Medium leads
Amazon Nova Lite: 25.5 (#123), Mistral Medium: 35.3 (#88)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Vision | 990 | 1172 |
Multilingual Mistral Medium leads
Amazon Nova Lite: 38.0 (#232), Mistral Medium: 52.1 (#91)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1208 | 1408 |
| LMArena Chinese | 1225 | 1447 |
| LMArena French | 1237 | 1459 |
| LMArena German | 1229 | 1432 |
| LMArena Japanese | 1153 | 1378 |
| LMArena Korean | 1153 | 1380 |
| LMArena Russian | 1216 | 1411 |
| LMArena Spanish | 1226 | 1433 |
Instruction Following Mistral Medium leads
Amazon Nova Lite: 59.3 (#255), Mistral Medium: 73.7 (#116)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1205 | 1398 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Mistral Medium leads
Amazon Nova Lite: 37.4 (#217), Mistral Medium: 42.9 (#114)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1234 | 1406 |
Writing & Preference Mistral Medium leads
Amazon Nova Lite: 42.1 (#237), Mistral Medium: 60.0 (#103)
| Benchmark | Amazon Nova Lite | Mistral Medium |
|---|---|---|
| LMArena Text | 1229 | 1424 |
| LMArena Creative Writing | 1197 | 1391 |
| LMArena Multi-Turn | 1199 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 31.9 on the Noometry Index. Amazon Nova Lite costs 29× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Lite or Mistral Medium?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Amazon Nova Lite or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 34.2 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 Medium share?
21 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Mistral Medium has 36.