Model comparison
Hy3 vs Mistral Small 3
Hy3 is the stronger model overall, scoring 44.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 2.5× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Tencent
Mistral AISummary
- They share 16 benchmarks with published results for both. Hy3 scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.0825 / $0.33 for Hy3.
- Hy3 accepts more context: 262K tokens versus 33K.
Side by side
| Hy3 | Mistral Small 3 | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.2 | 31.2 |
| Released | 2026-07-06 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.0825 | $0.05 |
| Output $ / M tokens | $0.33 | $0.08 |
| Results tracked | 19 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Mistral Small 3: 36.5 (#207)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1464 | 1246 |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Mistral Small 3: 18.9 (#273)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1233 |
| NYT Connections (extended) | 41.2% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |
Math Hy3 leads
Hy3: 40.1 (#93), Mistral Small 3: 16.3 (#295)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1475 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Mistral Small 3: 25.1 (#263)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1460 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Mistral Small 3: 37.3 (#236)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1426 | 1198 |
| LMArena Chinese | 1493 | 1204 |
| LMArena French | 1461 | 1203 |
| LMArena German | 1439 | 1211 |
| LMArena Japanese | 1392 | 1111 |
| LMArena Korean | 1395 | 1188 |
| LMArena Russian | 1432 | 1216 |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Mistral Small 3: 63.7 (#229)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1214 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Mistral Small 3: 37.8 (#211)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1442 | 1246 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Mistral Small 3: 32.2 (#280)
| Benchmark | Hy3 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1439 | 1234 |
| LMArena Creative Writing | 1402 | 1195 |
| LMArena Multi-Turn | 1436 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is Hy3 better than Mistral Small 3?
Hy3 is the stronger model overall, scoring 44.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 2.5× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.
Which is cheaper, Hy3 or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Hy3 lists at $0.0825 and $0.33.
Is Hy3 or Mistral Small 3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 33K.
How many benchmarks do Hy3 and Mistral Small 3 share?
16 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Mistral Small 3 has 24.