Model comparison
Devstral Small 2505 vs Qwen-14B
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 31.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 31.2.
Side by side
| Devstral Small 2505 | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 31.4 |
| Released | 2025-05-07 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.9 (#166), Qwen-14B: 31.2 (#288)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1071 |
Reasoning Too close to call
Devstral Small 2505: 19.7 (#252), Qwen-14B: 19.6 (#257)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Not comparable
Devstral Small 2505: —, Qwen-14B: 31.2 (#227)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Devstral Small 2505: —, Qwen-14B: —
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Not comparable
Devstral Small 2505: —, Qwen-14B: 27.5 (#275)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Devstral Small 2505: —, Qwen-14B: 52.4 (#289)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Devstral Small 2505: —, Qwen-14B: 31.3 (#280)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Not comparable
Devstral Small 2505: —, Qwen-14B: 27.6 (#299)
| Benchmark | Devstral Small 2505 | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Devstral Small 2505 better than Qwen-14B?
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 31.4 on the Noometry Index.
Is Devstral Small 2505 or Qwen-14B better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 31.2 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Qwen-14B share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen-14B has 18.