Model comparison
Hy3 vs Mixtral 8x22B
Hy3 is the stronger model overall, scoring 44.2 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
Mistral AISummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Mixtral 8x22B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 15.1.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Hy3 accepts more context: 262K tokens versus 64K.
Side by side
| Hy3 | Mixtral 8x22B | |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.2 | 27.1 |
| Released | 2026-07-06 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 262K | 64K |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.13 | $2 |
| Output $ / M tokens | $0.53 | $6 |
| Results tracked | 19 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1464 | 1166 |
| LMArena WebDev | 1508 | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Hy3: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1150 |
| NYT Connections (extended) | 41.2% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
Math Hy3 leads
Hy3: 40.1 (#93), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1475 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1460 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1426 | 1128 |
| LMArena Chinese | 1493 | 1116 |
| LMArena French | 1461 | 1166 |
| LMArena German | 1439 | 1141 |
| LMArena Japanese | 1392 | 1037 |
| LMArena Korean | 1395 | 1057 |
| LMArena Russian | 1432 | 1158 |
| LMArena Spanish | 1456 | 1151 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1147 |
| IFEval | — | 72.4% |
Long Context Hy3 leads
Hy3: 44.1 (#75), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1442 | 1144 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Hy3 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1439 | 1162 |
| LMArena Creative Writing | 1402 | 1141 |
| LMArena Multi-Turn | 1436 | 1130 |
| WildBench | — | 71.1% |
Frequently asked questions
Is Hy3 better than Mixtral 8x22B?
Hy3 is the stronger model overall, scoring 44.2 to 27.1 on the Noometry Index.
Which is cheaper, Hy3 or Mixtral 8x22B?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Hy3 or Mixtral 8x22B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 64K.
How many benchmarks do Hy3 and Mixtral 8x22B share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Mixtral 8x22B has 34.