reasoning benchmark
AutoLogi
AutoLogi is an automated method for synthesizing open-ended logic puzzles to evaluate reasoning abilities of Large Language Models. The benchmark addresses limitations of existing multiple-choice reasoning evaluations by featuring program-based verification and controllable difficulty levels. It includes 1,575 English and 883 Chinese puzzles, enabling more reliable evaluation that better distinguishes models' reasoning capabilities across languages.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
AutoLogi Ranking
Higher score ranks better on this benchmark.
| 1 | MA | 89.5% | 100.0% | 2 | C | |
| 2 | MA | 89.5% | 0.0% | 2 | C |
AutoLogi Score Distribution
A closer view of the leading scores on this benchmark.
AutoLogi Highlights
The leading models and scores on this benchmark.
What is AutoLogi?
What AutoLogi measures and how its scores work.
AutoLogi is an automated method for synthesizing open-ended logic puzzles to evaluate reasoning abilities of Large Language Models. The benchmark addresses limitations of existing multiple-choice reasoning evaluations by featuring program-based verification and controllable difficulty levels. It includes 1,575 English and 883 Chinese puzzles, enabling more reliable evaluation that better distinguishes models' reasoning capabilities across languages.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AutoLogi
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- autologi|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AutoLogi.
Which model scores highest on AutoLogi?
Kimi K2 Instruct is currently ranked first with 89.5%.
What does AutoLogi measure?
AutoLogi is an automated method for synthesizing open-ended logic puzzles to evaluate reasoning abilities of Large Language Models. The benchmark addresses limitations of existing multiple-choice reasoning evaluations by featuring program-based verification and controllable difficulty levels. It includes 1,575 English and 883 Chinese puzzles, enabling more reliable evaluation that better distinguishes models' reasoning capabilities across languages.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.