Model comparison
Amazon Nova Pro vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 31.7 to 30.5 on the Noometry Index. Amazon Nova Pro costs 2.1× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Amazon Nova Pro scores higher in 1 category and Pixtral Large in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Pro leads 44.1 to 32.9.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
- Pixtral Large has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Pixtral Large | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 30.5 | 31.7 |
| Released | 2024-12-03 | 2024-11-01 |
| Weights | Proprietary | Open |
| Context window | 300K | 128K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $6 |
| Results tracked | 38 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Amazon Nova Pro: 34.6 (#224), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| LiveBench Coding | 38.1% | — |
| LMArena Coding | 1270 | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.6 (#139), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Pixtral Large leads
Amazon Nova Pro: 19.2 (#240), Pixtral Large: 20.9 (#208)
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | 32.6% | — |
| LMArena Hard Prompts | 1246 | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.75 | — |
| LiveBench | 43.5% | — |
Math Not comparable
Amazon Nova Pro: 26.4 (#240), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| LMArena Math | 1252 | — |
Knowledge Not comparable
Amazon Nova Pro: 27.1 (#246), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| LMArena Expert | 1211 | — |
| MMLU | 82% | — |
Multimodal Pixtral Large leads
Amazon Nova Pro: 24.5 (#121), Pixtral Large: 30.0 (#105)
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| LMArena Vision | 980 | 1089 |
Multilingual Not comparable
Amazon Nova Pro: 39.9 (#218), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1234 | — |
| LMArena Chinese | 1244 | — |
| LMArena French | 1270 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1240 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Not comparable
Amazon Nova Pro: 65.1 (#221), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
| LMArena Instruction Following | 1235 | — |
Long Context Not comparable
Amazon Nova Pro: 38.1 (#199), Pixtral Large: —
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1255 | — |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 44.1 (#221), Pixtral Large: 32.9 (#273)
| Benchmark | Amazon Nova Pro | Pixtral Large |
|---|---|---|
| LMArena Text | 1259 | — |
| LMArena Creative Writing | 1212 | — |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 988 |
| WildBench | 77.7% | — |
| LMArena Multi-Turn | 1245 | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 31.7 to 30.5 on the Noometry Index. Amazon Nova Pro costs 2.1× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Pixtral Large?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 128K.
How many benchmarks do Amazon Nova Pro and Pixtral Large share?
1 benchmark has published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Pixtral Large has 3.