Model comparison
Mistral 7B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 23.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Yi-1.5-34B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 27.5 to 8.1.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 25.5% for Yi-1.5-34B.
Side by side
| Mistral 7B | Yi-1.5-34B | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 23.0 | 30.6 |
| Released | 2023-09-27 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Mistral 7B: 26.4 (#326), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 33.9% |
| LMArena Coding | 1082 | 1169 |
| BigCodeBench Complete | 27.3% | 43.8% |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Yi-1.5-34B leads
Mistral 7B: 13.1 (#336), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1160 |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Yi-1.5-34B leads
Mistral 7B: 8.1 (#325), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1085 | 1182 |
| MATH Level 5 | 3.7% | 25.5% |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| GSM8K | 54.4% | — |
Knowledge Yi-1.5-34B leads
Mistral 7B: 7.4 (#311), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 15.2% | 32% |
| LMArena Expert | 1036 | 1144 |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Yi-1.5-34B leads
Mistral 7B: 25.8 (#283), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1012 | 1121 |
| LMArena Chinese | 1009 | 1213 |
| LMArena French | 1037 | 1156 |
| LMArena German | 987 | 1111 |
| LMArena Japanese | 878 | 1021 |
| LMArena Russian | 1018 | 1091 |
| LMArena Spanish | 1026 | 1121 |
| LMArena Korean | — | 1005 |
Instruction Following Yi-1.5-34B leads
Mistral 7B: 54.2 (#280), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1139 |
Long Context Yi-1.5-34B leads
Mistral 7B: 32.2 (#271), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1060 | 1143 |
Writing & Preference Yi-1.5-34B leads
Mistral 7B: 30.7 (#286), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Mistral 7B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1090 | 1173 |
| LMArena Creative Writing | 1068 | 1135 |
| LMArena Multi-Turn | 1062 | 1153 |
Frequently asked questions
Is Mistral 7B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 23.0 on the Noometry Index.
Is Mistral 7B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Yi-1.5-34B share?
20 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Yi-1.5-34B has 21.