Model comparison
Mixtral 8x7B vs Yi-34B
Mixtral 8x7B and Yi-34B score almost the same on the Noometry Index (27.1 vs 27.8), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Mixtral 8x7B scores higher in 4 categories and Yi-34B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Yi-34B leads 56.2 to 51.0.
- The biggest single-benchmark swing is GPQA Diamond: 30.6% for Mixtral 8x7B and 14.7% for Yi-34B.
Side by side
| Mixtral 8x7B | Yi-34B | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 27.1 | 27.8 |
| Released | 2023-12-11 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 23 |
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-34B: 32.3 (#274)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Coding | 1126 | 1112 |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Yi-34B leads
Mixtral 8x7B: 18.2 (#285), Yi-34B: 21.2 (#226)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1104 |
| Epoch Capabilities Index | 118.47 | 117.39 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Yi-34B leads
Mixtral 8x7B: 18.8 (#289), Yi-34B: 21.6 (#282)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Math | 1147 | 1114 |
| MATH Level 5 | 10% | 5.1% |
| GSM8K | 74.4% | 76% |
| Omni-MATH | 10.5% | — |
Knowledge Mixtral 8x7B leads
Mixtral 8x7B: 11.0 (#301), Yi-34B: 7.5 (#309)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| GPQA Diamond | 30.6% | 14.7% |
| LMArena Expert | 1088 | 1061 |
| MMLU | 70.6% | 76.3% |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Too close to call
Mixtral 8x7B: 29.6 (#266), Yi-34B: 29.7 (#264)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1077 | 1079 |
| LMArena Chinese | 1055 | 1176 |
| LMArena French | 1166 | 1081 |
| LMArena German | 1114 | 1042 |
| LMArena Japanese | 931 | 993 |
| LMArena Korean | 968 | 959 |
| LMArena Russian | 1090 | 1050 |
| LMArena Spanish | 1111 | 1070 |
Instruction Following Yi-34B leads
Mixtral 8x7B: 51.0 (#297), Yi-34B: 56.2 (#274)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1109 | 1091 |
| IFEval | 57.5% | — |
Long Context Too close to call
Mixtral 8x7B: 33.4 (#260), Yi-34B: 33.2 (#264)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1103 | 1094 |
Writing & Preference Too close to call
Mixtral 8x7B: 34.2 (#270), Yi-34B: 34.1 (#273)
| Benchmark | Mixtral 8x7B | Yi-34B |
|---|---|---|
| LMArena Text | 1132 | 1129 |
| LMArena Creative Writing | 1109 | 1108 |
| LMArena Multi-Turn | 1115 | 1113 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Yi-34B?
Mixtral 8x7B and Yi-34B score almost the same on the Noometry Index (27.1 vs 27.8), so choose on price, context window or the category you care about most.
Is Mixtral 8x7B or Yi-34B better for coding?
They score almost the same on coding (32.8 vs 32.3); test both on your own repository before choosing.
How many benchmarks do Mixtral 8x7B and Yi-34B share?
22 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Yi-34B has 23.