Model comparison
Mixtral 8x22B vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 27.1 on the Noometry Index. Mixtral 8x22B costs 1.7× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Mistral AISummary
- They share 5 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Nova Premier 1.0 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nova Premier 1.0 leads 35.8 to 15.1.
- The biggest single-benchmark swing is MMLU-Pro: 46% for Mixtral 8x22B and 72.6% for Nova Premier 1.0.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | Nova Premier 1.0 | |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 27.1 | 38.3 |
| Released | 2024-04-17 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 64K | 1M |
| Max output | 64K | 10K |
| Input $ / M tokens | $2 | $2.50 |
| Output $ / M tokens | $6 | $12.50 |
| Results tracked | 34 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mixtral 8x22B: 24.2 (#329), Nova Premier 1.0: —
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| LMArena Coding | 1166 | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 23.1 (#127), Nova Premier 1.0: —
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Nova Premier 1.0 leads
Mixtral 8x22B: 19.9 (#248), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| LMArena Hard Prompts | 1150 | — |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122.03 | — |
| ForecastBench | 56.3 | — |
Math Nova Premier 1.0 leads
Mixtral 8x22B: 22.9 (#275), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 16.3% | 35% |
| LMArena Math | 1184 | — |
| MATH Level 5 | 24.2% | — |
Knowledge Nova Premier 1.0 leads
Mixtral 8x22B: 15.1 (#293), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 46% | 72.6% |
| GPQA (HELM) | 33.4% | 51.8% |
| GPQA Diamond | 34.1% | — |
| LMArena Expert | 1113 | — |
| MMLU | 77.8% | — |
Multilingual Not comparable
Mixtral 8x22B: 32.8 (#255), Nova Premier 1.0: —
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1128 | — |
| LMArena Chinese | 1116 | — |
| LMArena French | 1166 | — |
| LMArena German | 1141 | — |
| LMArena Japanese | 1037 | — |
| LMArena Korean | 1057 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1151 | — |
Instruction Following Nova Premier 1.0 leads
Mixtral 8x22B: 57.7 (#266), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| IFEval | 72.4% | 80.3% |
| LMArena Instruction Following | 1147 | — |
Long Context Not comparable
Mixtral 8x22B: 34.7 (#247), Nova Premier 1.0: —
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1144 | — |
Writing & Preference Nova Premier 1.0 leads
Mixtral 8x22B: 36.9 (#262), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Mixtral 8x22B | Nova Premier 1.0 |
|---|---|---|
| WildBench | 71.1% | 78.8% |
| LMArena Text | 1162 | — |
| LMArena Creative Writing | 1141 | — |
| LMArena Multi-Turn | 1130 | — |
Frequently asked questions
Is Mixtral 8x22B better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 27.1 on the Noometry Index. Mixtral 8x22B costs 1.7× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Which is cheaper, Mixtral 8x22B or Nova Premier 1.0?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 64K.
How many benchmarks do Mixtral 8x22B and Nova Premier 1.0 share?
5 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Nova Premier 1.0 has 6.