Model comparison
Mixtral 8x22B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 27.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 12 benchmarks with published results for both. Mixtral 8x22B scores higher in 4 categories and Wizardlm 70b in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 70b leads 32.2 to 22.9.
Side by side
| Mixtral 8x22B | Wizardlm 70b | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 27.1 | 33.0 |
| Released | 2024-04-17 | — |
| Weights | Open | Open |
| Context window | 64K | — |
| Max output | 64K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 34 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 70b leads
Mixtral 8x22B: 24.2 (#329), Wizardlm 70b: 31.4 (#285)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1166 | 1081 |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 23.1 (#127), Wizardlm 70b: —
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Too close to call
Mixtral 8x22B: 19.9 (#248), Wizardlm 70b: 20.7 (#234)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1079 |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122.03 | — |
| ForecastBench | 56.3 | — |
Math Wizardlm 70b leads
Mixtral 8x22B: 22.9 (#275), Wizardlm 70b: 32.2 (#218)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1184 | 1116 |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
Knowledge Not comparable
Mixtral 8x22B: 15.1 (#293), Wizardlm 70b: —
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| LMArena Expert | 1113 | — |
| MMLU | 77.8% | — |
Multilingual Mixtral 8x22B leads
Mixtral 8x22B: 32.8 (#255), Wizardlm 70b: 29.6 (#265)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1128 | 1078 |
| LMArena Chinese | 1116 | 1052 |
| LMArena German | 1141 | 1083 |
| LMArena Russian | 1158 | 1155 |
| LMArena French | 1166 | — |
| LMArena Japanese | 1037 | — |
| LMArena Korean | 1057 | — |
| LMArena Spanish | 1151 | — |
Instruction Following Mixtral 8x22B leads
Mixtral 8x22B: 57.7 (#266), Wizardlm 70b: 56.3 (#273)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1147 | 1093 |
| IFEval | 72.4% | — |
Long Context Mixtral 8x22B leads
Mixtral 8x22B: 34.7 (#247), Wizardlm 70b: 33.3 (#263)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1144 | 1097 |
Writing & Preference Mixtral 8x22B leads
Mixtral 8x22B: 36.9 (#262), Wizardlm 70b: 34.8 (#269)
| Benchmark | Mixtral 8x22B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1162 | 1120 |
| LMArena Creative Writing | 1141 | 1149 |
| LMArena Multi-Turn | 1130 | 1108 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 27.1 on the Noometry Index.
Is Mixtral 8x22B or Wizardlm 70b better for coding?
Wizardlm 70b scores higher on coding benchmarks: 31.4 versus 24.2 in the Noometry coding category.
How many benchmarks do Mixtral 8x22B and Wizardlm 70b share?
12 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Wizardlm 70b has 12.