Text-to-SQL on SParC
-0.43Kendall's TauLLaMA3.1-405B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLaMA3.1-405BRank subset=Ranks ≥ 32026.04 | -0.43 | -0.83 | |
| GPT-4o-miniRank subset=Ranks ≥ 32026.04 | -0.57 | -1 | |
| O3-miniRank subset=Ranks ≥ 32026.04 | -0.57 | -1 | |
| GPT-OSS-20Rank subset=Ranks ≥ 32026.04 | -0.64 | -1 | |
| LLaMA3.1-405BRank subset=All ranks2026.04 | -0.64 | -0.92 | |
| O3-miniRank subset=All ranks2026.04 | -0.69 | -0.95 | |
| GPT-OSS-20Rank subset=All ranks2026.04 | -0.73 | -1 | |
| GPT-4o-miniRank subset=All ranks2026.04 | -0.73 | -1 | |
| GPT-OSS-120Rank subset=Ranks ≥ 32026.04 | -0.79 | -1 | |
| LLaMA3.3-70BRank subset=Ranks ≥ 32026.04 | -0.79 | -1 | |
| GPT-OSS-120Rank subset=All ranks2026.04 | -0.82 | -0.95 | |
| LLaMA3.3-70BRank subset=All ranks2026.04 | -0.87 | -1 |