Multi-IF
Multi-IF benchmarks LLMs on multi-turn and multilingual instruction following. It expands upon IFEval by incorporating multi-turn sequences and translating English prompts into 7 other languages, resulting in 4,501 multilingual conversations with three turns each. The benchmark reveals that current leading LLMs struggle with maintaining accuracy in multi-turn instructions and shows higher error rates for non-Latin script languages.
Qwen3-235B-A22B-Thinking-2507 from Alibaba Cloud / Qwen Team currently leads the Multi-IF leaderboard with a score of 0.806 across 20 evaluated AI models.
Qwen3-235B-A22B-Thinking-2507 leads with 80.6%, followed by 
o3-mini at 79.5% and Qwen3 VL 235B A22B Thinking at 79.1%.
Progress Over Time
Interactive timeline showing model performance evolution on Multi-IF
Multi-IF Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 235B | 262K | $0.30 / $3.00 | ||
| 2 | OpenAI | — | 200K | $1.10 / $4.40 | ||
| 3 | Alibaba Cloud / Qwen Team | 236B | 262K | $0.45 / $3.49 | ||
| 4 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 5 | Alibaba Cloud / Qwen Team | 80B | 66K | $0.15 / $1.50 | ||
| 6 | Alibaba Cloud / Qwen Team | 235B | 262K | $0.15 / $0.80 | ||
| 7 | Alibaba Cloud / Qwen Team | 236B | 262K | $0.30 / $1.49 | ||
| 8 | Alibaba Cloud / Qwen Team | 80B | 66K | $0.15 / $1.50 | ||
| 9 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.18 / $2.09 | ||
| 9 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.08 / $0.50 | ||
| 11 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $1.00 | ||
| 12 | Alibaba Cloud / Qwen Team | 31B | 262K | $0.20 / $1.00 | ||
| 13 | Alibaba Cloud / Qwen Team | 31B | 128K | $0.10 / $0.44 | ||
| 14 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 15 | OpenAI | — | 1.0M | $2.00 / $8.00 | ||
| 15 | OpenAI | — | 128K | $75.00 / $150.00 | ||
| 17 | OpenAI | — | 1.0M | $0.40 / $1.60 | ||
| 18 | Alibaba Cloud / Qwen Team | 31B | 262K | $0.20 / $0.70 | ||
| 19 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 20 | OpenAI | — | 1.0M | $0.10 / $0.40 |
FAQ
Common questions about Multi-IF.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions