Model comparison
Mixtral 8x7B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mixtral 8x7B scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 11.0.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x7B | Yi-Lightning | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 27.1 | 37.1 |
| Released | 2023-12-11 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Mixtral 8x7B: 32.8 (#269), Yi-Lightning: 27.4 (#320)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1126 | 1312 |
| Aider Polyglot | — | 12.9% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Yi-Lightning leads
Mixtral 8x7B: 18.2 (#285), Yi-Lightning: 25.9 (#139)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1302 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Yi-Lightning leads
Mixtral 8x7B: 18.8 (#289), Yi-Lightning: 36.2 (#172)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1147 | 1300 |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Yi-Lightning leads
Mixtral 8x7B: 11.0 (#301), Yi-Lightning: 35.4 (#185)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1088 | 1286 |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Yi-Lightning leads
Mixtral 8x7B: 29.6 (#266), Yi-Lightning: 42.2 (#196)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1077 | 1269 |
| LMArena Chinese | 1055 | 1320 |
| LMArena French | 1166 | 1305 |
| LMArena German | 1114 | 1267 |
| LMArena Japanese | 931 | 1228 |
| LMArena Korean | 968 | 1192 |
| LMArena Russian | 1090 | 1255 |
| LMArena Spanish | 1111 | 1315 |
Instruction Following Yi-Lightning leads
Mixtral 8x7B: 51.0 (#297), Yi-Lightning: 67.4 (#196)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1109 | 1278 |
| IFEval | 57.5% | — |
Long Context Yi-Lightning leads
Mixtral 8x7B: 33.4 (#260), Yi-Lightning: 39.4 (#181)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1103 | 1297 |
Writing & Preference Yi-Lightning leads
Mixtral 8x7B: 34.2 (#270), Yi-Lightning: 50.2 (#184)
| Benchmark | Mixtral 8x7B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1132 | 1302 |
| LMArena Creative Writing | 1109 | 1280 |
| LMArena Multi-Turn | 1115 | 1311 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Yi-Lightning better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 27.4 in the Noometry coding category.
How many benchmarks do Mixtral 8x7B and Yi-Lightning share?
17 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Yi-Lightning has 18.