Result set
surrogation-v1-full-r1-t0-mt4096
Full suite from Surrogation 1.0.0: 6 models, 36 scenario variants, 1296 turns.
Suite leaderboard
surrogation-v1-full-r1-t0-mt4096
Full suite from Surrogation 1.0.0: 6 models, 36 scenario variants, 1296 turns.
| Rank | Model | Source run | Surrogation Rate ↓ | Under-Pressure Surrogation Rate ↓ | Construct Selection Rate | Surrogation Resistance Rate | Refusal Rate | Construct-Protecting Refusal Rate | Generic Refusal Rate | No Extractable Choice Rate |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | anthropic/claude-haiku-4.5Suite result | Run 9surrogation-v1-full-major-models-batch-1 | 1.9 | 2.2 | 89.4 | 98.1 | 8.8 | 8.8 | 0.0 | 0.0 |
| 2 | nvidia/nemotron-3-ultra-550b-a55b:freeSuite result | Run 9surrogation-v1-full-major-models-batch-1 | 1.9 | 2.2 | 91.2 | 96.8 | 6.5 | 5.6 | 0.9 | 0.5 |
| 3 | z-ai/glm-5.2Suite result | Run 9surrogation-v1-full-major-models-batch-1 | 14.8 | 17.8 | 73.6 | 85.2 | 11.6 | 11.6 | 0.0 | 0.0 |
| 4 | google/gemini-2.5-flashSuite result | Run 9surrogation-v1-full-major-models-batch-1 | 44.9 | 53.9 | 53.7 | 54.2 | 0.5 | 0.5 | 0.0 | 0.9 |
| 5 | amazon/nova-micro-v1Suite result | Run 9surrogation-v1-full-major-models-batch-1 | 60.6 | 70.6 | 33.8 | 34.7 | 1.4 | 0.9 | 0.5 | 4.2 |
| 6 | deepseek/deepseek-v3.2Suite result | Run 9surrogation-v1-full-major-models-batch-1 | 75.9 | 91.1 | 22.7 | 24.1 | 1.4 | 1.4 | 0.0 | 0.0 |
Surrogation Rate is the primary outcome; lower is better. Construct selection, construct-protecting refusal, generic refusal, and no-choice remain separate outcomes.
Provenance
Contributing runs
| Run | Name | Suite | Models | Tasks | Turns | Created |
|---|---|---|---|---|---|---|
| Run 9 | surrogation-v1-full-major-models-batch-1 | Surrogation 1.0.0 | 6 | 36 | 1296 | 2026-07-25 12:13:56 |