general benchmark
MAXIFE
MAXIFE is a multilingual benchmark evaluating LLMs on instruction following and execution across multiple languages and cultural contexts.
Updated Aug 7, 2026
Published models11
Registry coverage11
MetricScore
EvidenceB
MAXIFE leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 89.2% | 100.0% | 11 | C | |
| 2 | AC | 88.8% | 90.0% | 11 | C | |
| 3 | AC | 88.2% | 80.0% | 11 | C | |
| 4 | AC | 88.2% | 70.0% | 11 | C | |
| 5 | AC | 88.0% | 60.0% | 11 | C | |
| 6 | AC | 87.9% | 50.0% | 11 | C | |
| 7 | AC | 86.6% | 40.0% | 11 | C | |
| 8 | AC | 83.4% | 30.0% | 11 | C | |
| 9 | AC | 78.0% | 20.0% | 11 | C | |
| 10 | AC | 60.6% | 10.0% | 11 | C | |
| 11 | AC | 39.2% | 0.0% | 11 | C |
Score distribution
Top published rows on the benchmark's original scale.
MAXIFE highlights
The top published results on this benchmark's own scale.
What is MAXIFE?
Definition and scoring fields from the benchmark registry.
MAXIFE is a multilingual benchmark evaluating LLMs on instruction following and execution across multiple languages and cultural contexts.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MAXIFE
- Modality
- text
- Primary category
- general
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- maxife|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MAXIFE.
Which model scores highest on MAXIFE?
Qwen3.7 Max is currently ranked first with 89.2%.
What does MAXIFE measure?
MAXIFE is a multilingual benchmark evaluating LLMs on instruction following and execution across multiple languages and cultural contexts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
11 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.