Model
Mixtral-8x7B-Instruct-v0.1
Mistral AI · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ANLI | 55.2 | score | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 30.6 | accuracy | N/A | Independent | high | epoch.ai |
| HellaSwag | 86.7 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| MMLU | 70.6 | exact_match | N/A | Self-reported | medium | arxiv.org |
| MMLU | 70.5 | exact_match | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 85.8 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 83.6 | score | N/A | Self-reported | medium | arxiv.org |
| Trivia QA | 82.2 | exact_match | N/A | Independent | medium | arxiv.org |
| WinoGrande | 77.2 | accuracy | N/A | Self-reported | medium | arxiv.org |
| WinoGrande | 62.0 | accuracy | N/A | Independent | medium | arxiv.org |
Math
MathReproduced by the community
Loading community runs…