Model comparison
Hy4 preview vs Mistral Large 3
Hy4 preview is the stronger model overall, scoring 45.3 to 39.1 on the Noometry Index. Mistral Large 3 costs 3.0× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
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 3 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy4 preview leads 51.6 to 34.4.
- The biggest single-benchmark swing is NYT Connections (extended): 68.2% for Hy4 preview and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.75 / $2.25 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Mistral Large 3 | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 45.3 | 39.1 |
| Released | 2026-08-28 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 8K |
| Input $ / M tokens | $0.75 | $0.25 |
| Output $ / M tokens | $2.25 | $0.75 |
| Results tracked | 3 | 24 |
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 3: 34.4 (#237)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1632 | 1230 |
| LMArena Coding | — | 1448 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Mistral Large 3: 15.2 (#319)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 68.2% | 7.5% |
| Kagi LLM Benchmark | — | 50.9% |
| Thematic Generalization | — | 23% |
| LMArena Hard Prompts | — | 1429 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Mistral Large 3: 38.7 (#129)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1414 |
Knowledge Not comparable
Hy4 preview: —, Mistral Large 3: 36.0 (#177)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | — | 14.5% |
| LMArena Expert | — | 1421 |
Multimodal Not comparable
Hy4 preview: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Not comparable
Hy4 preview: —, Mistral Large 3: 52.5 (#84)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | — | 1413 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1455 |
| LMArena German | — | 1437 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1440 |
Instruction Following Not comparable
Hy4 preview: —, Mistral Large 3: 74.0 (#108)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | — | 1403 |
Long Context Not comparable
Hy4 preview: —, Mistral Large 3: 43.1 (#105)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | — | 1413 |
Writing & Preference Not comparable
Hy4 preview: —, Mistral Large 3: 60.0 (#101)
| Benchmark | Hy4 preview | Mistral Large 3 |
|---|---|---|
| LMArena Text | — | 1428 |
| LMArena Creative Writing | — | 1386 |
| EQ-Bench Creative Writing | — | 1412 |
| LMArena Multi-Turn | — | 1429 |
Frequently asked questions
Is Hy4 preview better than Mistral Large 3?
Hy4 preview is the stronger model overall, scoring 45.3 to 39.1 on the Noometry Index. Mistral Large 3 costs 3.0× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Hy4 preview lists at $0.75 and $2.25.
Is Hy4 preview or Mistral Large 3 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 34.4 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 Large 3 share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Mistral Large 3 has 24.