Model comparison
Mistral vs Yi-34B
Mistral is the stronger model overall, scoring 29.4 to 27.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral scores higher in 7 categories and Yi-34B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral leads 16.3 to 7.5.
- Yi-34B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Yi-34B | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 29.4 | 27.4 |
| Released | — | 2023-11-02 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.2 (#249), Yi-34B: 31.8 (#269)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Coding | 1162 | 1112 |
Reasoning Mistral leads
Mistral: 21.3 (#199), Yi-34B: 20.3 (#222)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.28 |
Math Too close to call
Mistral: 20.5 (#275), Yi-34B: 19.8 (#277)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Math | 1180 | 1114 |
| Omni-MATH | 7.2% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Mistral leads
Mistral: 16.3 (#283), Yi-34B: 7.5 (#304)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Expert | 1125 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| MMLU | — | 76.3% |
Multilingual Mistral leads
Mistral: 33.0 (#249), Yi-34B: 29.9 (#259)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Non-English | 1129 | 1079 |
| LMArena Chinese | 1109 | 1175 |
| LMArena French | 1179 | 1080 |
| LMArena German | 1155 | 1042 |
| LMArena Japanese | 1012 | 993 |
| LMArena Korean | 1032 | 959 |
| LMArena Russian | 1168 | 1050 |
| LMArena Spanish | 1143 | 1070 |
Instruction Following Yi-34B leads
Mistral: 52.9 (#283), Yi-34B: 56.4 (#269)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1091 |
| IFEval | 56.8% | — |
Long Context Mistral leads
Mistral: 35.0 (#240), Yi-34B: 33.2 (#259)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1154 | 1094 |
Writing & Preference Mistral leads
Mistral: 37.2 (#255), Yi-34B: 34.3 (#268)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Text | 1165 | 1129 |
| LMArena Creative Writing | 1158 | 1108 |
| LMArena Multi-Turn | 1147 | 1113 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Yi-34B?
Mistral is the stronger model overall, scoring 29.4 to 27.4 on the Noometry Index.
Is Mistral or Yi-34B better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 31.8 in the Noometry coding category.
How many benchmarks do Mistral and Yi-34B share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Yi-34B has 23.