Model comparison
Mistral 7B vs Yi-34B
Yi-34B is the stronger model overall, scoring 27.4 to 22.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Yi-34B in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-34B leads 19.8 to 7.6.
Side by side
| Mistral 7B | Yi-34B | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 22.9 | 27.4 |
| Released | 2023-09-27 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Mistral 7B: 25.9 (#321), Yi-34B: 31.8 (#269)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Coding | 1082 | 1112 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Yi-34B leads
Mistral 7B: 12.6 (#331), Yi-34B: 20.3 (#222)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1104 |
| BIG-Bench Hard | 56.1% | 71.7% |
| Epoch Capabilities Index | 111.97 | 117.28 |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Yi-34B leads
Mistral 7B: 7.6 (#319), Yi-34B: 19.8 (#277)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Math | 1085 | 1114 |
| MATH Level 5 | 3.7% | 5.1% |
| GSM8K | 54.4% | 76% |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
Knowledge Too close to call
Mistral 7B: 7.3 (#306), Yi-34B: 7.5 (#304)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| GPQA Diamond | 15.2% | 14.7% |
| LMArena Expert | 1036 | 1061 |
| MMLU | 62.5% | 76.3% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Yi-34B leads
Mistral 7B: 26.0 (#278), Yi-34B: 29.9 (#259)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1012 | 1079 |
| LMArena Chinese | 1009 | 1175 |
| LMArena French | 1036 | 1080 |
| LMArena German | 987 | 1042 |
| LMArena Japanese | 878 | 993 |
| LMArena Russian | 1018 | 1050 |
| LMArena Spanish | 1026 | 1070 |
| LMArena Korean | — | 959 |
Instruction Following Yi-34B leads
Mistral 7B: 54.5 (#275), Yi-34B: 56.4 (#269)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1091 |
Long Context Too close to call
Mistral 7B: 32.2 (#266), Yi-34B: 33.2 (#259)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1060 | 1094 |
Writing & Preference Yi-34B leads
Mistral 7B: 30.9 (#281), Yi-34B: 34.3 (#268)
| Benchmark | Mistral 7B | Yi-34B |
|---|---|---|
| LMArena Text | 1090 | 1129 |
| LMArena Creative Writing | 1068 | 1108 |
| LMArena Multi-Turn | 1062 | 1113 |
Frequently asked questions
Is Mistral 7B better than Yi-34B?
Yi-34B is the stronger model overall, scoring 27.4 to 22.9 on the Noometry Index.
Is Mistral 7B or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 31.8 versus 25.9 in the Noometry coding category.
How many benchmarks do Mistral 7B and Yi-34B share?
22 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Yi-34B has 23.