Model comparison
Mistral vs Yi-34B
Mistral is the stronger model overall, scoring 29.9 to 27.8 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 16.6 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 | 29.9 | 27.8 |
| 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: 33.8 (#250), Yi-34B: 32.3 (#274)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Coding | 1162 | 1112 |
Reasoning Mistral leads
Mistral: 22.2 (#200), Yi-34B: 21.2 (#226)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Too close to call
Mistral: 22.3 (#278), Yi-34B: 21.6 (#282)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Math | 1180 | 1114 |
| Omni-MATH | 7.2% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Mistral leads
Mistral: 16.6 (#288), Yi-34B: 7.5 (#309)
| 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: 32.8 (#254), Yi-34B: 29.7 (#264)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Non-English | 1129 | 1079 |
| LMArena Chinese | 1109 | 1176 |
| LMArena French | 1180 | 1081 |
| LMArena German | 1155 | 1042 |
| LMArena Japanese | 1013 | 993 |
| LMArena Korean | 1032 | 959 |
| LMArena Russian | 1168 | 1050 |
| LMArena Spanish | 1143 | 1070 |
Instruction Following Yi-34B leads
Mistral: 52.6 (#288), Yi-34B: 56.2 (#274)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1091 |
| IFEval | 56.8% | — |
Long Context Mistral leads
Mistral: 35.0 (#245), Yi-34B: 33.2 (#264)
| Benchmark | Mistral | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1153 | 1094 |
Writing & Preference Mistral leads
Mistral: 37.0 (#260), Yi-34B: 34.1 (#273)
| 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 29.9 to 27.8 on the Noometry Index.
Is Mistral or Yi-34B better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 32.3 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.