Model comparison
Hy4 preview vs Mistral Large 4
Hy4 preview is the stronger model overall, scoring 45.3 to 43.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
Tencent
Mistral AISummary
- They share 2 benchmarks with published results for both. Hy4 preview scores higher in 3 categories and Mistral Large 4 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 40.4.
- The biggest single-benchmark swing is NYT Connections (extended): 68.2% for Hy4 preview and 27.4% for Mistral Large 4.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $0.75 / $2.25 for Hy4 preview.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Mistral Large 4 | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 45.3 | 43.1 |
| Released | 2026-08-28 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 64K | 262K |
| Input $ / M tokens | $0.75 | $0.68 |
| Output $ / M tokens | $2.25 | $2.09 |
| Results tracked | 3 | 15 |
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 Large 4: 48.6 (#57)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| LMArena WebDev | 1632 | 1541 |
| LMArena Coding | — | 1475 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Mistral Large 4: 22.5 (#192)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| NYT Connections (extended) | 68.2% | 27.4% |
| LMArena Hard Prompts | — | 1444 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Mistral Large 4: 40.4 (#91)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1488 |
Knowledge Not comparable
Hy4 preview: —, Mistral Large 4: 36.6 (#166)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | — | 20% |
| LMArena Expert | — | 1447 |
Multilingual Not comparable
Hy4 preview: —, Mistral Large 4: 52.6 (#82)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | — | 1415 |
| LMArena Chinese | — | 1491 |
| LMArena Russian | — | 1414 |
Instruction Following Not comparable
Hy4 preview: —, Mistral Large 4: 75.0 (#76)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | — | 1424 |
Long Context Not comparable
Hy4 preview: —, Mistral Large 4: 43.6 (#89)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | — | 1429 |
Writing & Preference Not comparable
Hy4 preview: —, Mistral Large 4: 60.4 (#97)
| Benchmark | Hy4 preview | Mistral Large 4 |
|---|---|---|
| LMArena Text | — | 1427 |
| LMArena Creative Writing | — | 1361 |
| LMArena Multi-Turn | — | 1424 |
Frequently asked questions
Is Hy4 preview better than Mistral Large 4?
Hy4 preview is the stronger model overall, scoring 45.3 to 43.1 on the Noometry Index.
Which is cheaper, Hy4 preview or Mistral Large 4?
Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Hy4 preview lists at $0.75 and $2.25.
Is Hy4 preview or Mistral Large 4 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Hy4 preview and Mistral Large 4 share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Mistral Large 4 has 15.