reasoning benchmark
HumanEval+ Leaderboard
HumanEval+ is an enhanced version of HumanEval that extends the original test cases by 80x using the EvalPlus framework to evaluate the functional correctness of LLM-synthesized code.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
HumanEval+ Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score92.90% | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score92.30% | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelIB | Score86.09% | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelIB | Score86.09% | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelMI | Score82.80% | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelIB | Score78.30% | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelXI | Score75.60% | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score52.40% | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score51.20% | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelBA | Score25.00% | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
HumanEval+ Highlights
The leading models and scores on this benchmark.
HumanEval+ Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for HumanEval+
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is HumanEval+?
What HumanEval+ measures and how its scores work.
HumanEval+ is a reasoning benchmark for evaluating LLM-synthesized code with test cases extended by 80x from HumanEval using the EvalPlus framework.
It measures functional correctness using the Score metric, reported as a ratio, and detects previously undetected wrong code.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- HumanEval+
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about HumanEval+.
Which model scores highest on HumanEval+?
Phi 4 Reasoning is currently ranked first with 92.90%.
What are the top three models on HumanEval+?
The current leaders are Phi 4 Reasoning (92.90%), Phi 4 Reasoning Plus (92.30%), and Granite 3.3 8B Base (86.09%).
Which HumanEval+ model has the lowest official input price?
Phi 4 Reasoning has the lowest matched official input price at $0.13 input / $0.50 output per 1M tokens.
Which models are fastest among HumanEval+ results?
The fastest matched records are Phi 4 (33.00 tok/s via DeepInfra) and MiMo-V2.5-Pro (5.27 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.