Model comparison
Mixtral 8x7B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 27.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Mixtral 8x7B scores higher in 1 category and Yi-1.5-34B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 27.5 to 18.8.
- The biggest single-benchmark swing is MATH Level 5: 10% for Mixtral 8x7B and 25.5% for Yi-1.5-34B.
Side by side
| Mixtral 8x7B | Yi-1.5-34B | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 27.1 | 30.6 |
| Released | 2023-12-11 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mixtral 8x7B: 32.8 (#269), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1126 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Yi-1.5-34B leads
Mixtral 8x7B: 18.2 (#285), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1160 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Yi-1.5-34B leads
Mixtral 8x7B: 18.8 (#289), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1147 | 1182 |
| MATH Level 5 | 10% | 25.5% |
| Omni-MATH | 10.5% | — |
| GSM8K | 74.4% | — |
Knowledge Yi-1.5-34B leads
Mixtral 8x7B: 11.0 (#301), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 30.6% | 32% |
| LMArena Expert | 1088 | 1144 |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Yi-1.5-34B leads
Mixtral 8x7B: 29.6 (#266), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1077 | 1121 |
| LMArena Chinese | 1055 | 1213 |
| LMArena French | 1166 | 1156 |
| LMArena German | 1114 | 1111 |
| LMArena Japanese | 931 | 1021 |
| LMArena Korean | 968 | 1005 |
| LMArena Russian | 1090 | 1091 |
| LMArena Spanish | 1111 | 1121 |
Instruction Following Yi-1.5-34B leads
Mixtral 8x7B: 51.0 (#297), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1109 | 1139 |
| IFEval | 57.5% | — |
Long Context Yi-1.5-34B leads
Mixtral 8x7B: 33.4 (#260), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1103 | 1143 |
Writing & Preference Yi-1.5-34B leads
Mixtral 8x7B: 34.2 (#270), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Mixtral 8x7B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1132 | 1173 |
| LMArena Creative Writing | 1109 | 1135 |
| LMArena Multi-Turn | 1115 | 1153 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Yi-1.5-34B better for coding?
They score almost the same on coding (32.8 vs 32.4); test both on your own repository before choosing.
How many benchmarks do Mixtral 8x7B and Yi-1.5-34B share?
19 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Yi-1.5-34B has 21.