Model comparison
Amazon Nova Pro vs Mixtral 8x22B
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. Amazon Nova Pro scores higher in 8 categories and Mixtral 8x22B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Pro leads 27.4 to 15.1.
- The biggest single-benchmark swing is MMLU-Pro: 67.3% for Amazon Nova Pro and 46% for Mixtral 8x22B.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Amazon Nova Pro accepts more context: 300K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Mixtral 8x22B | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 31.0 | 27.1 |
| Released | 2024-12-03 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | 300K | 64K |
| Max output | 10K | 64K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $6 |
| Results tracked | 38 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1270 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Mixtral 8x22B leads
Amazon Nova Pro: 16.7 (#147), Mixtral 8x22B: 23.1 (#127)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| Cybench | — | 7.5% |
Reasoning Too close to call
Amazon Nova Pro: 20.0 (#243), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1150 |
| Epoch Capabilities Index | 123.8 | 122.03 |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 55.1% |
| LiveBench Data Analysis | 48.3% | — |
| ForecastBench | — | 56.3 |
| LiveBench | 43.5% | — |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 24.2% | 16.3% |
| LMArena Math | 1252 | 1184 |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 24.2% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| MMLU-Pro | 67.3% | 46% |
| GPQA (HELM) | 44.6% | 33.4% |
| LMArena Expert | 1211 | 1113 |
| MMLU | 82% | 77.8% |
| GPQA Diamond | — | 34.1% |
| Humanity's Last Exam | 4.4% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Mixtral 8x22B: —
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1234 | 1128 |
| LMArena Chinese | 1244 | 1116 |
| LMArena French | 1271 | 1166 |
| LMArena German | 1243 | 1141 |
| LMArena Japanese | 1200 | 1037 |
| LMArena Korean | 1203 | 1057 |
| LMArena Russian | 1240 | 1158 |
| LMArena Spanish | 1182 | 1151 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| IFEval | 81.5% | 72.4% |
| LMArena Instruction Following | 1235 | 1147 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1255 | 1144 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Amazon Nova Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1259 | 1162 |
| LMArena Creative Writing | 1212 | 1141 |
| WildBench | 77.7% | 71.1% |
| LMArena Multi-Turn | 1246 | 1130 |
| Short-Story Creative Writing | 60.5% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Mixtral 8x22B?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.1 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Mixtral 8x22B?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Amazon Nova Pro or Mixtral 8x22B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 64K.
How many benchmarks do Amazon Nova Pro and Mixtral 8x22B share?
24 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Mixtral 8x22B has 34.