Localization on FormalRx (test)
4,563ExMatchFormalRx-8B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| FormalRx-8B2026.07 | 4,563 | 707 | 75 | |
| Claude-Sonnet-4Model Type=Frontier Models2026.07 | 3,272 | 822 | 58.2 | |
| GPT-4.1Model Type=Frontier Models2026.07 | 3,261 | 963 | 60.9 | |
| GPT-5-miniModel Type=Frontier Models2026.07 | 3,164 | 1,175 | 61.7 | |
| GPT-5.3-CodexModel Type=Frontier Models2026.07 | 2,992 | 1,680 | 65.4 | |
| GPT-5.2Model Type=Frontier Models2026.07 | 2,594 | 1,378 | 56.5 | |
| Claude-Sonnet-4.6Model Type=Frontier Models2026.07 | 2,221 | 2,924 | 73.9 | |
| Qwen3-8BModel Type=Instruct Models2026.07 | 1,815 | 984 | 39.8 | |
| DeepSeek-v3.2Model Type=Frontier Models2026.07 | 1,770 | 1,094 | 40.7 | |
| Qwen3-4BModel Type=Instruct Models2026.07 | 1,054 | 1,276 | 33.1 | |
| Qwen3-1.7BModel Type=Instruct Models2026.07 | 874 | 1,584 | 35 |