Model comparison
Hy4 preview vs Mistral
Hy4 preview is the stronger model overall, scoring 45.3 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
Mistral AISummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 22.3.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Mistral | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 45.3 | 29.9 |
| Released | 2026-08-28 | — |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 3 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Mistral: 33.8 (#250)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1162 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Mistral: 22.2 (#200)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1149 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Mistral: 22.3 (#278)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| ProofBench | 75% | — |
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
Knowledge Not comparable
Hy4 preview: —, Mistral: 16.6 (#288)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Not comparable
Hy4 preview: —, Mistral: 32.8 (#254)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Not comparable
Hy4 preview: —, Mistral: 52.6 (#288)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |
Long Context Not comparable
Hy4 preview: —, Mistral: 35.0 (#245)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |
Writing & Preference Not comparable
Hy4 preview: —, Mistral: 37.0 (#260)
| Benchmark | Hy4 preview | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |
Frequently asked questions
Is Hy4 preview better than Mistral?
Hy4 preview is the stronger model overall, scoring 45.3 to 29.9 on the Noometry Index.
Is Hy4 preview or Mistral better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 33.8 in the Noometry coding category.
How many benchmarks do Hy4 preview and Mistral share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Mistral has 22.