Model comparison
Mixtral 8x22B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 26.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Mixtral 8x22B scores higher in 3 categories and Yi-1.5-34B in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Yi-1.5-34B leads 31.9 to 23.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 40.6% for Mixtral 8x22B and 33.9% for Yi-1.5-34B.
Side by side
| Mixtral 8x22B | Yi-1.5-34B | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 26.7 | 30.2 |
| Released | 2024-04-17 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 64K | — |
| Max output | 64K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Mixtral 8x22B: 23.8 (#324), Yi-1.5-34B: 31.9 (#267)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 40.6% | 33.9% |
| LMArena Coding | 1166 | 1169 |
| BigCodeBench Complete | 50.2% | 43.8% |
| WeirdML | 3.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 22.8 (#119), Yi-1.5-34B: —
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Yi-1.5-34B leads
Mixtral 8x22B: 19.1 (#246), Yi-1.5-34B: 21.5 (#195)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1160 |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122 | — |
| ForecastBench | 56.3 | — |
Math Yi-1.5-34B leads
Mixtral 8x22B: 21.2 (#271), Yi-1.5-34B: 25.3 (#248)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1184 | 1182 |
| MATH Level 5 | 24.2% | 25.5% |
| Omni-MATH | 16.3% | — |
Knowledge Too close to call
Mixtral 8x22B: 15.1 (#288), Yi-1.5-34B: 14.8 (#290)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 34.1% | 32% |
| LMArena Expert | 1113 | 1144 |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |
Multilingual Too close to call
Mixtral 8x22B: 32.9 (#250), Yi-1.5-34B: 32.5 (#251)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1128 | 1121 |
| LMArena Chinese | 1116 | 1213 |
| LMArena French | 1165 | 1155 |
| LMArena German | 1141 | 1111 |
| LMArena Japanese | 1037 | 1021 |
| LMArena Korean | 1056 | 1005 |
| LMArena Russian | 1158 | 1091 |
| LMArena Spanish | 1150 | 1120 |
Instruction Following Yi-1.5-34B leads
Mixtral 8x22B: 57.9 (#261), Yi-1.5-34B: 59.4 (#252)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1147 | 1139 |
| IFEval | 72.4% | — |
Long Context Too close to call
Mixtral 8x22B: 34.6 (#242), Yi-1.5-34B: 34.6 (#243)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1144 | 1144 |
Writing & Preference Too close to call
Mixtral 8x22B: 37.1 (#257), Yi-1.5-34B: 37.6 (#252)
| Benchmark | Mixtral 8x22B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1162 | 1173 |
| LMArena Creative Writing | 1141 | 1135 |
| LMArena Multi-Turn | 1130 | 1153 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 26.7 on the Noometry Index.
Is Mixtral 8x22B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 31.9 versus 23.8 in the Noometry coding category.
How many benchmarks do Mixtral 8x22B and Yi-1.5-34B share?
21 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Yi-1.5-34B has 21.