MixTAO-7Bx2-MoE-v8.1: benchmark results
zhengr's experimental 2x7B Mistral mixture-of-experts (~13B), a top scorer among small MoEs on the early-2024 Open LLM Leaderboard. Provider: Other. Released 2024-02-26. Access: Open.
Unified ELO 1501 ± 1, rank #684 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - TruthfulQA MC | 64.5 | Accuracy (%) | 96.1 |
| Open Korean LLM Leaderboard | 45.51 | Average Score (%) | 91.7 |
| Open LLM Leaderboard - MuSR | 15.29 | Score | 82.4 |
| Open Chinese LLM - WinoGrande | 65.04 | Accuracy (%) | 70.8 |
| Open Chinese LLM - HellaSwag | 61.49 | Accuracy (%) | 63.4 |
| Open LLM Leaderboard - BBH | 32.31 | Score | 60.6 |
| Open Chinese LLM Leaderboard | 57.73 | Average Score (%) | 60.5 |
| Open Chinese LLM - ARC Challenge | 53.33 | Accuracy (%) | 55.6 |
| Open LLM Leaderboard - GPQA | 6.49 | Score | 54.5 |
| Open Chinese LLM - GSM8K | 46.32 | Accuracy (%) | 53.1 |
| Open LLM Leaderboard - MATH Level 5 | 9.06 | Score | 44.4 |
| Open LLM Leaderboard - IFEval | 41.88 | Score | 42.7 |
Interactive version: theaggregate.ai/model?slug=mixtao-7bx2-moe-v8-1 · How It Works · Data refreshed daily, snapshot 2026-09-05.