Model comparison
Amazon Nova Pro vs Ministral 8B
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 28.2 on the Noometry Index. Ministral 8B costs 9.3× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Mistral AISummary
- They share 14 benchmarks with published results for both. Amazon Nova Pro scores higher in 9 categories and Ministral 8B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Pro leads 27.4 to 12.6.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 11.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 262K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Ministral 8B | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.0 | 28.2 |
| Released | 2024-12-03 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 262K |
| Input $ / M tokens | $0.80 | $0.15 |
| Output $ / M tokens | $3.20 | $0.15 |
| Results tracked | 38 | 17 |
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), Ministral 8B: 35.0 (#230)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Coding | 1270 | 1202 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Too close to call
Amazon Nova Pro: 16.7 (#147), Ministral 8B: 16.4 (#148)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 11.1% |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Ministral 8B: 18.4 (#281)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1191 |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 45.7% |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Ministral 8B: 25.7 (#267)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Math | 1252 | 1188 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 14.9% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Ministral 8B: 12.6 (#297)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 7.4% |
| LMArena Expert | 1211 | 1170 |
| GPQA Diamond | — | 27.1% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Ministral 8B: —
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Ministral 8B: 35.1 (#247)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1234 | 1165 |
| LMArena Chinese | 1244 | 1193 |
| LMArena Russian | 1240 | 1195 |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Ministral 8B: 60.5 (#250)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1161 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Ministral 8B: 36.7 (#227)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1255 | 1212 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Ministral 8B: 39.6 (#246)
| Benchmark | Amazon Nova Pro | Ministral 8B |
|---|---|---|
| LMArena Text | 1259 | 1191 |
| LMArena Creative Writing | 1212 | 1175 |
| LMArena Multi-Turn | 1246 | 1166 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Ministral 8B?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 28.2 on the Noometry Index. Ministral 8B costs 9.3× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Ministral 8B better for coding?
They score almost the same on coding (35.1 vs 35.0); 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 Ministral 8B share?
14 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Ministral 8B has 17.