Model comparison
Mixtral 8x7B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.1 on the Noometry Index. Mixtral 8x7B costs 2.0× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AI
StepFunSummary
- They share 13 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 5 Preview leads 41.2 to 11.0.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 32K.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x7B | Step 5 Preview | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 27.1 | 47.9 |
| Released | 2023-12-11 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 32K | 1.02M |
| Max output | 32K | 66K |
| Input $ / M tokens | $0.70 | $1 |
| Output $ / M tokens | $0.70 | $2.70 |
| Results tracked | 38 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Mixtral 8x7B: 32.8 (#269), Step 5 Preview: 51.8 (#36)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1126 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Step 5 Preview leads
Mixtral 8x7B: 18.2 (#285), Step 5 Preview: 40.0 (#57)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1465 |
| CritPt | — | 20.9% |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Step 5 Preview leads
Mixtral 8x7B: 18.8 (#289), Step 5 Preview: 46.1 (#72)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1147 | 1470 |
| ProofBench | — | 42% |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Step 5 Preview leads
Mixtral 8x7B: 11.0 (#301), Step 5 Preview: 41.2 (#112)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1088 | 1470 |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multimodal Not comparable
Mixtral 8x7B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Mixtral 8x7B: 29.6 (#266), Step 5 Preview: 53.8 (#54)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1077 | 1432 |
| LMArena Chinese | 1055 | 1519 |
| LMArena Russian | 1090 | 1436 |
| LMArena Spanish | 1111 | 1439 |
| LMArena French | 1166 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
Instruction Following Step 5 Preview leads
Mixtral 8x7B: 51.0 (#297), Step 5 Preview: 76.0 (#50)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1109 | 1444 |
| IFEval | 57.5% | — |
Long Context Step 5 Preview leads
Mixtral 8x7B: 33.4 (#260), Step 5 Preview: 44.5 (#64)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1103 | 1455 |
Writing & Preference Step 5 Preview leads
Mixtral 8x7B: 34.2 (#270), Step 5 Preview: 62.8 (#71)
| Benchmark | Mixtral 8x7B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1132 | 1442 |
| LMArena Creative Writing | 1109 | 1410 |
| LMArena Multi-Turn | 1115 | 1447 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.1 on the Noometry Index. Mixtral 8x7B costs 2.0× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Mixtral 8x7B or Step 5 Preview?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Mixtral 8x7B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 32K.
How many benchmarks do Mixtral 8x7B and Step 5 Preview share?
13 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Step 5 Preview has 18.