HumanEval+
HumanEval+ is the EvalPlus extension of HumanEval with 80x more generated unit tests for correctness checking. Score recorded from the Bonsai 2 27B GGUF card's Full Per-Benchmark Results (thinking mode, EvalScope + vLLM on NVIDIA H100).
Category
Code
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for HumanEval+
| Model | Score | Date | Verified |
|---|---|---|---|
| Bonsai 2 27B — GGUF |
100.00%
|
17.09.2026 | Verified |
| Kolibri-1 |
92.70
|
03.10.2026 | Verified |