Model comparison
Hy3 vs Ministral 8B
Hy3 is the stronger model overall, scoring 44.2 to 28.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Tencent
Mistral AISummary
- They share 12 benchmarks with published results for both. Hy3 scores higher in 8 categories and Ministral 8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 12.6.
- Both cost about the same: $0.0825 input and $0.33 output per million tokens.
Side by side
| Hy3 | Ministral 8B | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.2 | 28.2 |
| Released | 2026-07-06 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.0825 | $0.15 |
| Output $ / M tokens | $0.33 | $0.15 |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Ministral 8B: 35.0 (#230)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1464 | 1202 |
| LMArena WebDev | 1508 | — |
Agentic & Tool Use Not comparable
Hy3: —, Ministral 8B: 16.4 (#148)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Ministral 8B: 18.4 (#281)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1191 |
| NYT Connections (extended) | 41.2% | — |
| DTBench | — | 45.7% |
Math Hy3 leads
Hy3: 40.1 (#93), Ministral 8B: 25.7 (#267)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Math | 1475 | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Ministral 8B: 12.6 (#297)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Expert | 1460 | 1170 |
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Ministral 8B: 35.1 (#247)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1426 | 1165 |
| LMArena Chinese | 1493 | 1193 |
| LMArena Russian | 1432 | 1195 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Ministral 8B: 60.5 (#250)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1161 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Ministral 8B: 36.7 (#227)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1442 | 1212 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Ministral 8B: 39.6 (#246)
| Benchmark | Hy3 | Ministral 8B |
|---|---|---|
| LMArena Text | 1439 | 1191 |
| LMArena Creative Writing | 1402 | 1175 |
| LMArena Multi-Turn | 1436 | 1166 |
Frequently asked questions
Is Hy3 better than Ministral 8B?
Hy3 is the stronger model overall, scoring 44.2 to 28.2 on the Noometry Index.
Which is cheaper, Hy3 or Ministral 8B?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Ministral 8B lists at $0.15 and $0.15.
Is Hy3 or Ministral 8B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Ministral 8B share?
12 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Ministral 8B has 17.