New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
MLogiQA benchmark
AI model leaderboard for the MLogiQA benchmark. Compare how large language models score on MLogiQA, see the full ranking, and understand what this AI benchmark measures. Qwen3-235B-A22B currently leads with 77.1. Multilingual logical-reasoning QA benchmark — Chinese LogiQA + multilingual translations.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Qwen3-235B-A22B | Qwen | 77.1 | thinking | official ↗ |
| #2 | Qwen3-32B | Qwen | 76.3 | thinking | official ↗ |
| #3 | Qwen3-14B | Qwen | 71.1 | thinking | official ↗ |
| #4 | Qwen3-30B-A3B | Qwen | 70.1 | thinking | official ↗ |
| #5 | Qwen3-8B | Qwen | 69 | thinking | official ↗ |
| #6 | Qwen3-235B-A22B | Qwen | 67.6 | non-thinking | official ↗ |
| #7 | Qwen3-4B | Qwen | 65.9 | thinking | official ↗ |
| #8 | Qwen3-32B | Qwen | 62.9 | non-thinking | official ↗ |
| #9 | Qwen3-14B | Qwen | 58.9 | non-thinking | official ↗ |
| #10 | Qwen3-1.7B | Qwen | 56 | thinking | official ↗ |
| #11 | Qwen3-30B-A3B | Qwen | 53.3 | non-thinking | official ↗ |
| #12 | Qwen3-8B | Qwen | 51.4 | non-thinking | official ↗ |
| #13 | Qwen3-4B | Qwen | 49.9 | non-thinking | official ↗ |
| #14 | Qwen3-1.7B | Qwen | 41.1 | non-thinking | official ↗ |
| #15 | Qwen3-0.6B | Qwen | 40.9 | thinking | official ↗ |
| #16 | Qwen3-0.6B | Qwen | 37.3 | non-thinking | official ↗ |
Frequently asked questions about MLogiQA
What is the MLogiQA benchmark?
Multilingual logical-reasoning QA benchmark — Chinese LogiQA + multilingual translations.
How is the MLogiQA benchmark scored?
MLogiQA is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on MLogiQA?
As of the latest reported scores on GenAIList, Qwen3-235B-A22B achieves the highest result on MLogiQA with a score of 77.1.
Is a higher MLogiQA score better?
Yes. On MLogiQA a higher score indicates better performance, so models near the top of the leaderboard are the strongest.