agents benchmark
MLE-Bench Lite Leaderboard
MLE-Bench Lite evaluates AI agents on machine learning engineering tasks, testing their ability to build, train, and optimize ML models for Kaggle-style competitions in a lightweight evaluation format.
Updated Aug 17, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MLE-Bench Lite Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score66.6% | Percentile100.0% | Participants1 | EvidenceC | Evaluated |
MLE-Bench Lite Highlights
The leading models and scores on this benchmark.
The Top AI Models for MLE-Bench Lite
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mle-bench lite AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MIMiniMax M2.7MiniMax
- Score
- 66.6%
- Price
- $0.30 input / $1.2 output per 1M tokens
- Speed
- Up to 102 tok/s via MiniMax
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MLE-Bench Lite, not total model capability
Selection summary
Best AI Models for MLE-Bench Lite
MiniMax M2.7 currently leads MLE-Bench Lite with 66.6%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is MLE-Bench Lite?
What MLE-Bench Lite measures and how its scores work.
MLE-Bench Lite evaluates AI agents on machine learning engineering tasks, testing their ability to build, train, and optimize ML models for Kaggle-style competitions in a lightweight evaluation format.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MLE-Bench Lite
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mle-bench-lite|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MLE-Bench Lite.
Which model scores highest on MLE-Bench Lite?
MiniMax M2.7 is currently ranked first with 66.6%.
What does MLE-Bench Lite measure?
MLE-Bench Lite evaluates AI agents on machine learning engineering tasks, testing their ability to build, train, and optimize ML models for Kaggle-style competitions in a lightweight evaluation format.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.