Model comparison
Devstral Small 2505 vs Hunyuan Large Vision
Hunyuan Large Vision is the stronger model overall, scoring 37.6 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
TencentSummary
- The widest gap is in reasoning, where Hunyuan Large Vision leads 24.8 to 19.7.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Hunyuan Large Vision | |
|---|---|---|
| Provider | Mistral AI | Tencent |
| Noometry Index | 34.3 | 37.6 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Devstral Small 2505: 38.9 (#166), Hunyuan Large Vision: 38.3 (#180)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1308 |
Reasoning Hunyuan Large Vision leads
Devstral Small 2505: 19.7 (#252), Hunyuan Large Vision: 24.8 (#158)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1257 |
Math Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 35.5 (#183)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Math | — | 1268 |
Knowledge Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 34.4 (#196)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Expert | — | 1252 |
Multimodal Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 35.7 (#83)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Vision | — | 1180 |
Multilingual Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 39.9 (#221)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1287 |
| LMArena Russian | — | 1243 |
Instruction Following Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 65.8 (#215)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Instruction Following | — | 1251 |
Long Context Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 38.9 (#189)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Longer Query | — | 1280 |
Writing & Preference Not comparable
Devstral Small 2505: —, Hunyuan Large Vision: 46.5 (#218)
| Benchmark | Devstral Small 2505 | Hunyuan Large Vision |
|---|---|---|
| LMArena Text | — | 1263 |
| LMArena Creative Writing | — | 1248 |
| LMArena Multi-Turn | — | 1254 |
Frequently asked questions
Is Devstral Small 2505 better than Hunyuan Large Vision?
Hunyuan Large Vision is the stronger model overall, scoring 37.6 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or Hunyuan Large Vision better for coding?
They score almost the same on coding (38.9 vs 38.3); test both on your own repository before choosing.
How many benchmarks do Devstral Small 2505 and Hunyuan Large Vision share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Hunyuan Large Vision has 13.