Model comparison
Mixtral 8x22B vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 31.4 to 27.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Mixtral 8x22B scores higher in 5 categories and Qwen-14B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mixtral 8x22B leads 36.9 to 27.6.
Side by side
| Mixtral 8x22B | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 31.4 |
| Released | 2024-04-17 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 64K | — |
| Max output | 64K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Mixtral 8x22B: 24.2 (#329), Qwen-14B: 31.2 (#288)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1166 | 1071 |
| 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), Qwen-14B: —
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Too close to call
Mixtral 8x22B: 19.9 (#248), Qwen-14B: 19.6 (#257)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1027 |
| Epoch Capabilities Index | 122.03 | 113.03 |
| DTBench | 55.1% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 56.3 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Mixtral 8x22B: 22.9 (#275), Qwen-14B: 31.2 (#227)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Math | 1184 | 1068 |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Mixtral 8x22B: 15.1 (#293), Qwen-14B: —
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| MMLU | 77.8% | 66.3% |
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multilingual Mixtral 8x22B leads
Mixtral 8x22B: 32.8 (#255), Qwen-14B: 27.5 (#275)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1128 | 1041 |
| LMArena Chinese | 1116 | 1077 |
| LMArena French | 1166 | — |
| LMArena German | 1141 | — |
| LMArena Japanese | 1037 | — |
| LMArena Korean | 1057 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1151 | — |
Instruction Following Mixtral 8x22B leads
Mixtral 8x22B: 57.7 (#266), Qwen-14B: 52.4 (#289)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1147 | 1031 |
| IFEval | 72.4% | — |
Long Context Mixtral 8x22B leads
Mixtral 8x22B: 34.7 (#247), Qwen-14B: 31.3 (#280)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1144 | 1028 |
Writing & Preference Mixtral 8x22B leads
Mixtral 8x22B: 36.9 (#262), Qwen-14B: 27.6 (#299)
| Benchmark | Mixtral 8x22B | Qwen-14B |
|---|---|---|
| LMArena Text | 1162 | 1051 |
| LMArena Creative Writing | 1141 | 1028 |
| LMArena Multi-Turn | 1130 | 1022 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 31.4 to 27.1 on the Noometry Index.
Is Mixtral 8x22B or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 24.2 in the Noometry coding category.
How many benchmarks do Mixtral 8x22B and Qwen-14B share?
12 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Qwen-14B has 18.