Mungert/Youtu-LLM-2B-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MATH-500 | math | 84.8 | MATH-500 | medium | | MATH-500 | 84.8% | 89.8% | 91.8% | **95.0%** | 90.8% | <u>93.7%</u> | |
| HumanEval | coding | 64.0 | HumanEval | medium | | HumanEval | 64.0% | 84.8% | 79.9% | <u>95.4%<u> | 88.1% | **95.9%** | |
| SWE-bench Verified | swe | 60.0 | SWE-Bench-Verified | medium | | SWE-Bench-Verified | 0.6% | <u>7.2%</u> | 5.7% | **17.7%** | |
| HumanEval | coding | 59.5 | HumanEval+ | medium | | HumanEval+ | 59.5% | 76.2% | 74.7% | <u>87.8%</u> | 82.5% | **89.0%** | |
| BFCL (function calling) | agentic | 55.5 | BFCL V3 | medium | | BFCL V3 | 55.5% | 31.5% | **61.7%** | <u>58.0%</u> | |
| MMLU | knowledge | 53.0 | MMLU-Redux | medium | | MMLU-Redux | 53.0% | 74.1% | 75.6% | **83.8%** | <u>78.1%</u> | 75.8% | |
| MBPP | coding | 51.5 | MBPP | medium | | MBPP | 51.5% | 80.5% | 66.7% | **92.3%** | 73.9% | <u>85.0%</u> | |
| MBPP | coding | 44.2 | MBPP+ | medium | | MBPP+ | 44.2% | 67.7% | 56.7% | **77.6%** | 61.0% | <u>71.7%</u> | |
| MUSR | reasoning | 43.8 | MUSR | medium | | MUSR | 43.8% | 56.6% | 54.1% | **60.5%** | <u>59.7%</u> | 57.4% | |
| DROP | reasoning | 41.3 | DROP | medium | | DROP | 41.3% | 72.5% | 72.0% | <u>82.9%<u> | 73.1% | **86.7%** | |
| MMLU-Pro | knowledge | 36.5 | MMLU-Pro | medium | | MMLU-Pro | 36.5% | 54.9% | 53.0% | **69.1%** | 57.5% | <u>61.6%</u> | |
| GPQA Diamond | reasoning | 33.6 | GPQA-Diamond | medium | | GPQA-Diamond | 33.6% | 36.9% | 43.8% | **55.2%** | 45.5% | <u>48.0%</u> | |
| BBH | reasoning | 31.0 | BBH | medium | | BBH | 31.0% | 69.1% | 76.3% | **87.8%** | <u>77.8%</u> | 77.5% | |
| IFEval | instruction-following | 29.4 | IFEval | medium | | IFEval | 29.4% | 70.4% | 60.4% | **83.6%** | 34.6% | <u>81.2%</u> | |
| LiveCodeBench | coding | 19.8 | LiveCodeBench v6 | medium | | LiveCodeBench v6 | 19.8% | 30.7% | 30.8% | **48.5%** | 36.8% | <u>43.7%</u> | |
none scraped.