New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Multi-IF (EN) benchmark
AI model leaderboard for the Multi-IF (EN) benchmark. Compare how large language models score on Multi-IF (EN), see the full ranking, and understand what this AI benchmark measures. EXAONE 4.0 (32B) currently leads with 73.5%. Multi-turn instruction-following benchmark, English subset.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | EXAONE 4.0 (32B) | LG AI Research | 73.5% | reasoning | official ↗ |
| #2 | EXAONE 4.0 (1.2B) | LG AI Research | 53.9% | reasoning | official ↗ |
Frequently asked questions about Multi-IF (EN)
What is the Multi-IF (EN) benchmark?
Multi-turn instruction-following benchmark, English subset.
How is the Multi-IF (EN) benchmark scored?
Multi-IF (EN) is scored using the accuracy (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on Multi-IF (EN)?
As of the latest reported scores on GenAIList, EXAONE 4.0 (32B) achieves the highest result on Multi-IF (EN) with a score of 73.5%.
Is a higher Multi-IF (EN) score better?
Yes. On Multi-IF (EN) a higher score indicates better performance, so models near the top of the leaderboard are the strongest.