Model comparison
Mixtral 8x7B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 27.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
StepFunSummary
- They share 12 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Step 2 16k Exp 202412 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 2 16k Exp 202412 leads 35.2 to 11.0.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x7B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 27.1 | 39.2 |
| Released | 2023-12-11 | — |
| Weights | Open | Proprietary |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Mixtral 8x7B: 32.8 (#269), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1126 | 1316 |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Step 2 16k Exp 202412 leads
Mixtral 8x7B: 18.2 (#285), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1299 |
| 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 2 16k Exp 202412 leads
Mixtral 8x7B: 18.8 (#289), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1147 | 1304 |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Step 2 16k Exp 202412 leads
Mixtral 8x7B: 11.0 (#301), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1088 | 1279 |
| 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% | — |
Multilingual Step 2 16k Exp 202412 leads
Mixtral 8x7B: 29.6 (#266), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1077 | 1290 |
| LMArena Chinese | 1055 | 1331 |
| LMArena Russian | 1090 | 1324 |
| LMArena French | 1166 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Step 2 16k Exp 202412 leads
Mixtral 8x7B: 51.0 (#297), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1109 | 1287 |
| IFEval | 57.5% | — |
Long Context Step 2 16k Exp 202412 leads
Mixtral 8x7B: 33.4 (#260), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1103 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Mixtral 8x7B: 34.2 (#270), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Mixtral 8x7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1132 | 1321 |
| LMArena Creative Writing | 1109 | 1328 |
| LMArena Multi-Turn | 1115 | 1292 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 32.8 in the Noometry coding category.
How many benchmarks do Mixtral 8x7B and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Step 2 16k Exp 202412 has 12.