LLM Similarity Measurement on RL Models
100Similarity ScoreLogits
Evaluation Results
| Method | Links | |
|---|---|---|
| LogitsRL Model/Algorithm=Archer-Code-1.5B (GRPO)2026.07 | 100 | |
| GhostSpecRL Model/Algorithm=Archer-Code-1.5B (GRPO)2026.07 | 100 | |
| LogitsRL Model/Algorithm=Nemotron-Research-Reasoning-Qwen-1.5B (Reinforcement++)2026.07 | 100 | |
| GhostSpecRL Model/Algorithm=Nemotron-Research-Reasoning-Qwen-1.5B (Reinforcement++)2026.07 | 100 | |
| PCSRL Model/Algorithm=Polaris-7B-Preview (DAPO)2026.07 | 100 | |
| LogitsRL Model/Algorithm=Polaris-7B-Preview (DAPO)2026.07 | 100 | |
| PCSRL Model/Algorithm=Archer-Code-1.5B (GRPO)2026.07 | 99 | |
| Spectral SignatureRL Model/Algorithm=Archer-Code-1.5B (GRPO)2026.07 | 99 | |
| PCSRL Model/Algorithm=Nemotron-Research-Reasoning-Qwen-1.5B (Reinforcement++)2026.07 | 99 | |
| Spectral SignatureRL Model/Algorithm=Nemotron-Research-Reasoning-Qwen-1.5B (Reinforcement++)2026.07 | 99 | |
| Spectral SignatureRL Model/Algorithm=Polaris-7B-Preview (DAPO)2026.07 | 99 | |
| REEFRL Model/Algorithm=Archer-Code-1.5B (GRPO)2026.07 | 98 | |
| REEFRL Model/Algorithm=Nemotron-Research-Reasoning-Qwen-1.5B (Reinforcement++)2026.07 | 96 | |
| REEFRL Model/Algorithm=Polaris-7B-Preview (DAPO)2026.07 | 94 | |
| GhostSpecRL Model/Algorithm=Polaris-7B-Preview (DAPO)2026.07 | 46 |