structured output benchmark
SIFO
SIFO (Simple Instruction Following) evaluates how well language models follow simple, explicit instructions. It tests fundamental instruction-following capabilities across various task types.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
SIFO leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.773 points | 100.0% | 1 | C |
SIFO highlights
The top published results on this benchmark's own scale.
What is SIFO?
Definition and scoring fields from the benchmark registry.
SIFO (Simple Instruction Following) evaluates how well language models follow simple, explicit instructions. It tests fundamental instruction-following capabilities across various task types.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SIFO
- Modality
- text
- Primary category
- structured output
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- sifo|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SIFO.
Which model scores highest on SIFO?
Qwen3 VL 235B A22B Thinking is currently ranked first with 0.773 points.
What does SIFO measure?
SIFO (Simple Instruction Following) evaluates how well language models follow simple, explicit instructions. It tests fundamental instruction-following capabilities across various task types.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.