Model comparison
Mistral Small vs Qwen-14B
Mistral Small is the stronger model overall, scoring 33.1 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Qwen-14B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.6 to 27.8.
Side by side
| Mistral Small | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.1 | 30.8 |
| Released | 2024-02-26 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 39 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Mistral Small: 33.5 (#242), Qwen-14B: 30.6 (#283)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Coding | 1363 | 1072 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 27.9 (#87), Qwen-14B: —
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Too close to call
Mistral Small: 19.3 (#238), Qwen-14B: 18.7 (#255)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1336 | 1027 |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| LiveBench | 44% | — |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Mistral Small: 15.4 (#287), Qwen-14B: 28.7 (#224)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Math | 1341 | 1068 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Mistral Small: 30.9 (#214), Qwen-14B: —
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| MMLU | 68.7% | 66.3% |
| GPQA Diamond | 47.5% | — |
| Vectara Hallucination Rate | 5.1% | — |
| LMArena Expert | 1293 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multimodal Not comparable
Mistral Small: 32.9 (#91), Qwen-14B: —
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Mistral Small leads
Mistral Small: 45.7 (#164), Qwen-14B: 27.7 (#270)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1315 | 1042 |
| LMArena Chinese | 1342 | 1077 |
| LMArena French | 1337 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1260 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Mistral Small leads
Mistral Small: 66.6 (#204), Qwen-14B: 52.6 (#284)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1031 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Mistral Small leads
Mistral Small: 40.4 (#151), Qwen-14B: 31.3 (#276)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1327 | 1029 |
Writing & Preference Mistral Small leads
Mistral Small: 52.6 (#165), Qwen-14B: 27.8 (#294)
| Benchmark | Mistral Small | Qwen-14B |
|---|---|---|
| LMArena Text | 1338 | 1051 |
| LMArena Creative Writing | 1304 | 1028 |
| LMArena Multi-Turn | 1344 | 1022 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen-14B?
Mistral Small is the stronger model overall, scoring 33.1 to 30.8 on the Noometry Index.
Is Mistral Small or Qwen-14B better for coding?
Mistral Small scores higher on coding benchmarks: 33.5 versus 30.6 in the Noometry coding category.
How many benchmarks do Mistral Small and Qwen-14B share?
11 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen-14B has 18.