Model comparison
Mistral 7B vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 30.8 to 22.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral 7B scores higher in 3 categories and Qwen-14B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 28.7 to 7.6.
Side by side
| Mistral 7B | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 22.9 | 30.8 |
| Released | 2023-09-27 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Mistral 7B: 25.9 (#321), Qwen-14B: 30.6 (#283)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1082 | 1072 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Qwen-14B leads
Mistral 7B: 12.6 (#331), Qwen-14B: 18.7 (#255)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1027 |
| BIG-Bench Hard | 56.1% | 55% |
| Epoch Capabilities Index | 111.97 | 112.8 |
| PIQA | 83% | 79.9% |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| HellaSwag | 81% | — |
| LAMBADA | — | 71.1% |
| WinoGrande | 75.3% | — |
Math Qwen-14B leads
Mistral 7B: 7.6 (#319), Qwen-14B: 28.7 (#224)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Math | 1085 | 1068 |
| GSM8K | 54.4% | 61.3% |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
Knowledge Not comparable
Mistral 7B: 7.3 (#306), Qwen-14B: —
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 78.6% | 84.4% |
| BoolQ | 87.4% | 86.2% |
| MMLU | 62.5% | 66.3% |
| GPQA Diamond | 15.2% | — |
| LMArena Expert | 1036 | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Qwen-14B leads
Mistral 7B: 26.0 (#278), Qwen-14B: 27.7 (#270)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1012 | 1042 |
| LMArena Chinese | 1009 | 1077 |
| LMArena French | 1036 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Russian | 1018 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Mistral 7B leads
Mistral 7B: 54.5 (#275), Qwen-14B: 52.6 (#284)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1031 |
Long Context Too close to call
Mistral 7B: 32.2 (#266), Qwen-14B: 31.3 (#276)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1060 | 1029 |
Writing & Preference Mistral 7B leads
Mistral 7B: 30.9 (#281), Qwen-14B: 27.8 (#294)
| Benchmark | Mistral 7B | Qwen-14B |
|---|---|---|
| LMArena Text | 1090 | 1051 |
| LMArena Creative Writing | 1068 | 1028 |
| LMArena Multi-Turn | 1062 | 1022 |
Frequently asked questions
Is Mistral 7B better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 30.8 to 22.9 on the Noometry Index.
Is Mistral 7B or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 30.6 versus 25.9 in the Noometry coding category.
How many benchmarks do Mistral 7B and Qwen-14B share?
17 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen-14B has 18.