Model comparison
Hy4 preview vs Mistral Medium
Hy4 preview is the stronger model overall, scoring 44.6 to 36.0 on the Noometry Index.
Last verified . 1 shared benchmarks.
Tencent
Mistral AISummary
- They share 1 benchmark with published results for both. Hy4 preview scores higher in 3 categories and Mistral Medium in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 54.5 to 27.2.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 9% for Mistral Medium.
- Hy4 preview is cheaper at $0.83 / $2.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Mistral Medium | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.6 | 36.0 |
| Released | 2026-08-28 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 262K |
| Input $ / M tokens | $0.83 | $1.50 |
| Output $ / M tokens | $2.50 | $7.50 |
| Results tracked | 3 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.4 (#36), Mistral Medium: 33.8 (#241)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| FrontierCode | — | 8% |
| LMArena WebDev | 1633 | — |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| LMArena Coding | — | 1434 |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Hy4 preview: —, Mistral Medium: 28.1 (#84)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Hy4 preview leads
Hy4 preview: 30.6 (#75), Mistral Medium: 23.3 (#165)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Hy4 preview leads
Hy4 preview: 54.5 (#37), Mistral Medium: 27.2 (#238)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| ProofBench | 75% | 9% |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| LMArena Math | — | 1409 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Not comparable
Hy4 preview: —, Mistral Medium: 24.9 (#260)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
Hy4 preview: —, Mistral Medium: 34.6 (#82)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Not comparable
Hy4 preview: —, Mistral Medium: 52.3 (#86)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1460 |
| LMArena German | — | 1433 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1382 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Not comparable
Hy4 preview: —, Mistral Medium: 73.9 (#111)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1398 |
Long Context Not comparable
Hy4 preview: —, Mistral Medium: 42.9 (#108)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |
Writing & Preference Not comparable
Hy4 preview: —, Mistral Medium: 60.2 (#97)
| Benchmark | Hy4 preview | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is Hy4 preview better than Mistral Medium?
Hy4 preview is the stronger model overall, scoring 44.6 to 36.0 on the Noometry Index.
Which is cheaper, Hy4 preview or Mistral Medium?
Hy4 preview is cheaper. It lists at $0.83 per million input tokens and $2.50 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Hy4 preview or Mistral Medium better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 262K.
How many benchmarks do Hy4 preview and Mistral Medium share?
1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Mistral Medium has 36.