Model comparison
Hy3 vs Mistral 7B
Hy3 is the stronger model overall, scoring 43.6 to 22.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Tencent
Mistral AISummary
- They share 14 benchmarks with published results for both. Hy3 scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.2 to 7.3.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- Hy3 accepts more context: 262K tokens versus 8K.
Side by side
| Hy3 | Mistral 7B | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 43.6 | 22.9 |
| Released | 2026-07-06 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 262K | 8K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.13 | $0.25 |
| Output $ / M tokens | $0.53 | $0.25 |
| Results tracked | 17 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Mistral 7B: 25.9 (#321)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Coding | 1465 | 1082 |
| LMArena WebDev | 1509 | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Hy3 leads
Hy3: 25.0 (#134), Mistral 7B: 12.6 (#331)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1067 |
| NYT Connections (extended) | 41.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 111.97 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Hy3 leads
Hy3: 37.4 (#98), Mistral 7B: 7.6 (#319)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Math | 1475 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Hy3 leads
Hy3: 40.2 (#108), Mistral 7B: 7.3 (#306)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Expert | 1461 | 1036 |
| GPQA Diamond | — | 15.2% |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Mistral 7B: 26.0 (#278)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1427 | 1012 |
| LMArena Chinese | 1496 | 1009 |
| LMArena French | 1461 | 1036 |
| LMArena Russian | 1435 | 1018 |
| LMArena Spanish | 1448 | 1026 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Korean | 1390 | — |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Mistral 7B: 54.5 (#275)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1425 | 1060 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Mistral 7B: 32.2 (#266)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1443 | 1060 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Mistral 7B: 30.9 (#281)
| Benchmark | Hy3 | Mistral 7B |
|---|---|---|
| LMArena Text | 1442 | 1090 |
| LMArena Creative Writing | 1399 | 1068 |
| LMArena Multi-Turn | 1436 | 1062 |
Frequently asked questions
Is Hy3 better than Mistral 7B?
Hy3 is the stronger model overall, scoring 43.6 to 22.9 on the Noometry Index.
Which is cheaper, Hy3 or Mistral 7B?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Mistral 7B lists at $0.25 and $0.25.
Is Hy3 or Mistral 7B better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 25.9 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 8K.
How many benchmarks do Hy3 and Mistral 7B share?
14 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Mistral 7B has 37.