Model comparison
Hy3 vs Magistral Medium
Hy3 is the stronger model overall, scoring 44.2 to 35.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
Mistral AISummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 26.1 to 8.6.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $2 / $5 for Magistral Medium.
Side by side
| Hy3 | Magistral Medium | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.2 | 35.2 |
| Released | 2026-07-06 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.0825 | $2 |
| Output $ / M tokens | $0.33 | $5 |
| Results tracked | 19 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Magistral Medium: 39.1 (#161)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Coding | 1464 | 1319 |
| LMArena WebDev | 1508 | — |
| SciCode | — | 39.2% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Magistral Medium: 8.6 (#348)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 41.2% | — |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
Math Hy3 leads
Hy3: 40.1 (#93), Magistral Medium: 35.1 (#189)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Math | 1475 | 1250 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Magistral Medium: 33.5 (#202)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1460 | 1223 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Magistral Medium: 39.6 (#224)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1426 | 1232 |
| LMArena Chinese | 1493 | 1227 |
| LMArena French | 1461 | 1267 |
| LMArena German | 1439 | 1248 |
| LMArena Japanese | 1392 | 1175 |
| LMArena Korean | 1395 | 1125 |
| LMArena Russian | 1432 | 1224 |
| LMArena Spanish | 1456 | 1271 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Magistral Medium: 66.0 (#211)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1426 | 1254 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Magistral Medium: 39.3 (#183)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1442 | 1295 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Magistral Medium: 46.3 (#219)
| Benchmark | Hy3 | Magistral Medium |
|---|---|---|
| LMArena Text | 1439 | 1255 |
| LMArena Creative Writing | 1402 | 1245 |
| LMArena Multi-Turn | 1436 | 1275 |
Frequently asked questions
Is Hy3 better than Magistral Medium?
Hy3 is the stronger model overall, scoring 44.2 to 35.2 on the Noometry Index.
Which is cheaper, Hy3 or Magistral Medium?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Magistral Medium lists at $2 and $5.
Is Hy3 or Magistral Medium better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Magistral Medium share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Magistral Medium has 22.