Model comparison
Mistral Small 3 vs Qwen-14B
Mistral Small 3 and Qwen-14B score almost the same on the Noometry Index (30.9 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Mistral Small 3 scores higher in 5 categories and Qwen-14B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 28.7 to 15.3.
Side by side
| Mistral Small 3 | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 30.8 |
| Released | 2025-01-30 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.0 (#203), Qwen-14B: 30.6 (#283)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1246 | 1072 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Too close to call
Mistral Small 3: 18.2 (#269), Qwen-14B: 18.7 (#255)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1027 |
| Epoch Capabilities Index | 127.06 | 112.8 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Mistral Small 3: 15.3 (#290), Qwen-14B: 28.7 (#224)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Math | 1240 | 1068 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Mistral Small 3: 25.0 (#258), Qwen-14B: —
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
| LMArena Expert | 1202 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Mistral Small 3 leads
Mistral Small 3: 37.5 (#231), Qwen-14B: 27.7 (#270)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1198 | 1042 |
| LMArena Chinese | 1204 | 1077 |
| LMArena French | 1202 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |
Instruction Following Mistral Small 3 leads
Mistral Small 3: 63.9 (#224), Qwen-14B: 52.6 (#284)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1031 |
Long Context Mistral Small 3 leads
Mistral Small 3: 37.8 (#206), Qwen-14B: 31.3 (#276)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1246 | 1029 |
Writing & Preference Mistral Small 3 leads
Mistral Small 3: 32.4 (#275), Qwen-14B: 27.8 (#294)
| Benchmark | Mistral Small 3 | Qwen-14B |
|---|---|---|
| LMArena Text | 1234 | 1051 |
| LMArena Creative Writing | 1195 | 1028 |
| LMArena Multi-Turn | 1217 | 1022 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Qwen-14B?
Mistral Small 3 and Qwen-14B score almost the same on the Noometry Index (30.9 vs 30.8), so choose on price, context window or the category you care about most.
Is Mistral Small 3 or Qwen-14B better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 30.6 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Qwen-14B share?
11 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen-14B has 18.