Model comparison
Devstral Small 2505 vs Hy3
Hy3 is the stronger model overall, scoring 43.6 to 33.9 on the Noometry Index. Devstral Small 2505 costs 1.5× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
TencentSummary
- The widest gap is in coding, where Hy3 leads 46.6 to 38.6.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.13 / $0.53 for Hy3.
- Hy3 accepts more context: 262K tokens versus 128K.
Side by side
| Devstral Small 2505 | Hy3 | |
|---|---|---|
| Provider | Mistral AI | Tencent |
| Noometry Index | 33.9 | 43.6 |
| Released | 2025-05-07 | 2026-07-06 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.10 | $0.13 |
| Output $ / M tokens | $0.30 | $0.53 |
| Results tracked | 4 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Devstral Small 2505: 38.6 (#160), Hy3: 46.6 (#60)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1509 |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1465 |
Reasoning Hy3 leads
Devstral Small 2505: 19.1 (#243), Hy3: 25.0 (#134)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 41.2% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1449 |
Math Not comparable
Devstral Small 2505: —, Hy3: 37.4 (#98)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| LMArena Math | — | 1475 |
Knowledge Not comparable
Devstral Small 2505: —, Hy3: 40.2 (#108)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| LMArena Expert | — | 1461 |
Multilingual Not comparable
Devstral Small 2505: —, Hy3: 53.7 (#60)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1496 |
| LMArena French | — | 1461 |
| LMArena Korean | — | 1390 |
| LMArena Russian | — | 1435 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
Devstral Small 2505: —, Hy3: 75.3 (#68)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| LMArena Instruction Following | — | 1425 |
Long Context Not comparable
Devstral Small 2505: —, Hy3: 44.1 (#70)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1443 |
Writing & Preference Not comparable
Devstral Small 2505: —, Hy3: 62.5 (#75)
| Benchmark | Devstral Small 2505 | Hy3 |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1399 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is Devstral Small 2505 better than Hy3?
Hy3 is the stronger model overall, scoring 43.6 to 33.9 on the Noometry Index. Devstral Small 2505 costs 1.5× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Hy3?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Hy3 lists at $0.13 and $0.53.
Is Devstral Small 2505 or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 38.6 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Hy3 share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Hy3 has 17.