Model comparison
Hy3 vs Magistral Small
Hy3 is the stronger model overall, scoring 44.2 to 30.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
Mistral AISummary
- The widest gap is in reasoning, where Hy3 leads 26.1 to 6.8.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Hy3 accepts more context: 262K tokens versus 128K.
Side by side
| Hy3 | Magistral Small | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.2 | 30.2 |
| Released | 2026-07-06 | 2025-06-10 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 128K | 40K |
| Input $ / M tokens | $0.0825 | $0.50 |
| Output $ / M tokens | $0.33 | $1.50 |
| Results tracked | 19 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Magistral Small: 38.4 (#176)
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| LMArena WebDev | 1508 | — |
| SciCode | — | 35.2% |
| LMArena Coding | 1464 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Magistral Small: 6.8 (#350)
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 6.3% |
| NYT Connections (extended) | 41.2% | — |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 3% |
| LMArena Hard Prompts | 1447 | — |
| DTBench | — | 61.3% |
| Epoch Capabilities Index | — | 133.19 |
Math Hy3 leads
Hy3: 40.1 (#93), Magistral Small: 26.2 (#261)
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 30% |
| LMArena Math | 1475 | — |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Magistral Small: 30.9 (#223)
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | 1460 | — |
Multilingual Not comparable
Hy3: 53.5 (#65), Magistral Small: —
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| LMArena Non-English | 1426 | — |
| LMArena Chinese | 1493 | — |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Russian | 1432 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Not comparable
Hy3: 75.1 (#70), Magistral Small: —
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1426 | — |
Long Context Not comparable
Hy3: 44.1 (#75), Magistral Small: —
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1442 | — |
Writing & Preference Not comparable
Hy3: 62.2 (#81), Magistral Small: —
| Benchmark | Hy3 | Magistral Small |
|---|---|---|
| LMArena Text | 1439 | — |
| LMArena Creative Writing | 1402 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Hy3 better than Magistral Small?
Hy3 is the stronger model overall, scoring 44.2 to 30.2 on the Noometry Index.
Which is cheaper, Hy3 or Magistral Small?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Magistral Small lists at $0.50 and $1.50.
Is Hy3 or Magistral Small better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 38.4 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 128K.
How many benchmarks do Hy3 and Magistral Small share?
0 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Magistral Small has 10.