🚨 the "Mythos 69%" headline is misleading
GPT-5.5 Codex sits at 41%, looks close.
on T1 (full control, the only tier that matters):
Mythos: 16 envs
GPT-5.5 Codex: 2
Opus 4.7: 0
9x gap, not 1.7x.
baseline Mythos (no hints) hits MORE T1s than nudged(hints). it doesn't need
36
405
24
62.7K
Snapshot History (27)
| Date | ||||
|---|---|---|---|---|
| May 18 · 06:00 | 36 | +3 405 | +1 24 | +595 62.7K |
| May 18 · 00:00 | 36 | +1 402 | 23 | +167 62.1K |
| May 17 · 23:00 | 36 | +1 401 | 23 | +447 62.0K |
| May 17 · 20:00 | 36 | 400 | 23 | +195 61.5K |
| May 17 · 19:00 | 36 | 400 | 23 | +255 61.3K |
| May 17 · 18:00 | 36 | 400 | 23 | +306 61.1K |
| May 17 · 17:00 | +1 36 | +4 400 | 23 | +2.2K 60.7K |
| May 17 · 14:00 | 35 | +1 396 | 23 | +749 58.6K |
| May 17 · 13:00 | 35 | +2 395 | 23 | +1.4K 57.8K |
| May 17 · 11:00 | 35 | +2 393 | 23 | +812 56.4K |
| May 17 · 10:00 | +1 35 | +2 391 | 23 | +1.6K 55.6K |
| May 17 · 08:00 | 34 | +2 389 | 23 | +879 54.1K |
| May 17 · 07:00 | 34 | +1 387 | 23 | +845 53.2K |
| May 17 · 06:00 | 34 | +1 386 | 23 | +804 52.3K |
| May 17 · 05:00 | +1 34 | +1 385 | +1 23 | +740 51.5K |
| May 17 · 04:00 | +1 33 | +21 384 | +2 22 | +3.1K 50.8K |
| May 17 · 01:00 | 32 | +1 363 | 20 | +1.1K 47.7K |
| May 17 · 00:00 | 32 | +2 362 | +1 20 | +1.1K 46.7K |
| May 16 · 23:00 | 32 | +6 360 | 19 | +1.3K 45.6K |
| May 16 · 22:00 | 32 | +6 354 | 19 | +1.9K 44.3K |
| May 16 · 21:00 | +2 32 | +16 348 | 19 | +3.4K 42.4K |
| May 16 · 19:00 | 30 | +5 332 | 19 | +1.7K 39.0K |
| May 16 · 18:00 | +1 30 | +8 327 | 19 | +2.1K 37.2K |
| May 16 · 17:00 | +1 29 | +9 319 | +1 19 | +2.6K 35.1K |
| May 16 · 16:00 | +1 28 | +13 310 | 18 | +4.6K 32.5K |
| May 16 · 15:00 | +5 27 | +51 297 | +6 18 | +8.5K 28.0K |
| May 16 · 13:00 | +22 22 | +246 246 | +12 12 | +19.5K 19.5K |
| May 16 · 08:52 | 0 | 0 | 0 | 0 |