Exact labels from the selected evaluator. Historical model labels are preserved; availability, licenses, and current API aliases should be checked with the publisher.
Loading catalog…
Published evidence. Clear sources. No sponsored rank placement.
How to read these results →125 models · HumanEval+ · Higher is better
Python function generation tested against EvalPlus expanded tests. Higher pass@1 is better. Ranks apply only to this source snapshot and selected metric. Arena ranks are preserved from the source; other ranks use exact scores. Small differences do not establish statistical superiority.
| Compare | Rank | Model / evaluated label | HumanEval+ | Mode | Parameters | Source |
|---|---|---|---|---|---|---|
| #16 | OpenCoder-8B-Instructinfly | 77.4% | Instruction | 8B | Evidence | |
| #23 | Artigenz-Coder-DS-6.7BArtigenz | 72.6% | Instruction | 6.7B | Evidence | |
| #61 | Code-13Bajibawa-2023 | 52.4% | Instruction | 13B | Evidence | |
| #54 | Code-290k-6.7B-Instructajibawa-2023 | 59.7% | Instruction | 6.7B | Evidence | |
| #68 | Code-33Bajibawa-2023 | 49.4% | Instruction | 33B | Evidence | |
| #93 | CodeGen-16BNot specified | 28.0% | Completion | 16B | Evidence | |
| #103 | CodeGen-2BNot specified | 22.6% | Completion | 2B | Evidence | |
| #96 | CodeGen-6BNot specified | 25.6% | Completion | 6B | Evidence | |
| #110 | CodeGen2-16BNot specified | 16.5% | Completion | 16B | Evidence | |
| #121 | CodeGen2-1BNot specified | 9.1% | Completion | 1B | Evidence | |
| #115 | CodeGen2-3BNot specified | 12.8% | Completion | 3B | Evidence | |
| #108 | CodeGen2-7BNot specified | 17.7% | Completion | 7B | Evidence | |
| #81 | CodeLlama-13BNot specified | 38.4% | Completion | 13B | Evidence | |
| #74 | CodeLlama-34BNot specified | 43.9% | Completion | 34B | Evidence | |
| #64 | CodeLlama-70Bcodellama | 50.6% | Completion | 70B | Evidence | |
| #42 | CodeLlama-70B-Instructcodellama | 65.9% | Instruction | 70B | Evidence | |
| #85 | CodeLlama-7BNot specified | 35.4% | Completion | 7B | Evidence | |
| #3 | Qwen2.5-Coder-32B-InstructQwen | 87.2% | Instruction | 32B | Evidence | |
| #70 | CodeQwen1.5-7BQwen | 45.7% | Completion | 7B | Evidence | |
| #15 | CodeQwen1.5-7B-ChatQwen | 78.7% | Instruction | 7B | Evidence | |
| #55 | Qwen1.5-72B-ChatQwen | 59.1% | Instruction | 72B | Evidence | |
| #95 | CodeT5+-16BNot specified | 26.8% | Completion | 16B | Evidence | |
| #104 | CodeT5+-2BNot specified | 22.0% | Completion | 2B | Evidence | |
| #100 | CodeT5+-6BNot specified | 24.4% | Completion | 6B | Evidence | |
| #58 | Command-R+CohereForAI | 56.7% | Instruction | 104B | Evidence |
#61
Code-13B#68
Code-33B#93
CodeGen-16B#103
CodeGen-2B#96
CodeGen-6B#110
CodeGen2-16B#121
CodeGen2-1B#115
CodeGen2-3B#108
CodeGen2-7B#85
CodeLlama-7B#95
CodeT5+-16B#104
CodeT5+-2B#100
CodeT5+-6B#58
Command-R+EvalPlus contributors — results redistributed under Apache-2.0. Normalized by BuildnScale; no evaluations rerun. Parameter counts and instruction labels are source metadata. Namespace is shown where supplied; it is not a verified API provider or license classification.