Model comparison
Devstral Small 2505 vs Hunyuan Turbos 20250226
Hunyuan Turbos 20250226 is the stronger model overall, scoring 40.6 to 33.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
TencentSummary
- The widest gap is in reasoning, where Hunyuan Turbos 20250226 leads 26.7 to 19.1.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Hunyuan Turbos 20250226 | |
|---|---|---|
| Provider | Mistral AI | Tencent |
| Noometry Index | 33.9 | 40.6 |
| Released | 2025-05-07 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Devstral Small 2505: 38.6 (#160), Hunyuan Turbos 20250226: 39.3 (#148)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1361 |
Reasoning Hunyuan Turbos 20250226 leads
Devstral Small 2505: 19.1 (#243), Hunyuan Turbos 20250226: 26.7 (#115)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1374 |
Math Not comparable
Devstral Small 2505: —, Hunyuan Turbos 20250226: 34.8 (#155)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Math | — | 1359 |
Knowledge Not comparable
Devstral Small 2505: —, Hunyuan Turbos 20250226: 36.4 (#158)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Expert | — | 1338 |
Multilingual Not comparable
Devstral Small 2505: —, Hunyuan Turbos 20250226: 49.1 (#132)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Non-English | — | 1362 |
| LMArena Chinese | — | 1416 |
| LMArena French | — | 1390 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1338 |
| LMArena Korean | — | 1351 |
| LMArena Russian | — | 1368 |
Instruction Following Not comparable
Devstral Small 2505: —, Hunyuan Turbos 20250226: 71.2 (#153)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Instruction Following | — | 1344 |
Long Context Not comparable
Devstral Small 2505: —, Hunyuan Turbos 20250226: 41.6 (#132)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Longer Query | — | 1365 |
Writing & Preference Not comparable
Devstral Small 2505: —, Hunyuan Turbos 20250226: 57.5 (#125)
| Benchmark | Devstral Small 2505 | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Text | — | 1377 |
| LMArena Creative Writing | — | 1358 |
| LMArena Multi-Turn | — | 1387 |
Frequently asked questions
Is Devstral Small 2505 better than Hunyuan Turbos 20250226?
Hunyuan Turbos 20250226 is the stronger model overall, scoring 40.6 to 33.9 on the Noometry Index.
Is Devstral Small 2505 or Hunyuan Turbos 20250226 better for coding?
They score almost the same on coding (38.6 vs 39.3); test both on your own repository before choosing.
How many benchmarks do Devstral Small 2505 and Hunyuan Turbos 20250226 share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Hunyuan Turbos 20250226 has 16.