Convergence Results
54 total runs
| Date | Model | γ Overall | Tests | Passes | |
|---|---|---|---|---|---|
| 2026-06-06T14:47 | moonshot-v1-128k | 0.1892 | 40/40 | 5 | view → |
| 2026-06-06T15:20 | deepseek-chat | 0.0811 | 40/40 | 5 | view → |
| 2026-06-06T18:18 | Kimi-K2.5 | 0.1351 | 40/40 | 5 | view → |
| 2026-06-06T17:51 | gpt-5.4-nano | 0.0556 | 40/40 | 5 | view → |
| 2026-06-06T17:21 | DeepSeek-V3.2 | 0.0556 | 40/40 | 5 | view → |
| 2026-06-06T16:45 | grok-4-20-reasoning | 0.1389 | 40/40 | 5 | view → |
| 2026-06-06T10:18 | claude-sonnet-4-6 | 0.0270 | 40/40 | 5 | view → |
| 2026-06-05T13:02 | gpt-4.1 | 0.0270 | 40/40 | 5 | view → |
| 2026-06-06T02:20 | grok-build-0.1 | 0.0811 | 40/40 | 5 | view → |
| 2026-06-06T08:28 | claude-sonnet-4-6 | 0.0541 | 40/40 | 5 | view → |
| 2026-06-03T14:02 | hermes-3-llama-3.1-8b | 0.0811 | 40/40 | 5 | view → |
| 2026-06-03T13:20 | Kimi-K2.5 | 0.1538 | 35/40 | 5 | view → |
| 2026-06-03T12:50 | DeepSeek-V3.2 | n/a | 39/40 | 5 | view → |
| 2026-06-03T12:24 | gpt-5.4-nano | 0.0541 | 40/40 | 5 | view → |
| 2026-06-03T11:58 | gpt-4o | 0.1081 | 40/40 | 5 | view → |
| 2026-06-03T11:12 | grok-4-20-reasoning | 0.2000 | 38/40 | 5 | view → |
| 2026-06-03T10:02 | Kimi-K2.5 | 0.2857 | 38/40 | 5 | view → |
| 2026-06-03T06:20 | hermes-3-llama-3.1-8b | 0.0556 | 40/40 | 5 | view → |
| 2026-06-03T08:22 | Kimi-K2.5 | 0.2727 | 36/40 | 5 | view → |
| 2026-06-03T07:47 | DeepSeek-V3.2 | 0.0278 | 39/40 | 5 | view → |