MysteryMechanism
As of Nov 3, 2026, MysteryMechanism (v1) is maintained by Vals AI. Metric accuracy (%). Ceiling 100. Saturation unknown. Contamination risk low.
- Maintainer
- Vals AI
- Metric
- accuracy (%)
- Ceiling
- 100
- Saturation
- unknown
- Contamination
- low
- Cadence
- Declared cadence: as Vals updates (checked daily). Catalog snapshots: 1, latest Oct 30, 2026.
- Source
- Vals AI · this benchmark on Vals AI
- Grading
- Automatic (tests or exact checks) — The recovered expression is run on private probes and passes below a noise-aware error threshold.
Source: Vals AI. A proprietary private test set run by Vals; scores are republished with permission. Rows are dated the day isitsota first saw them, and only the benchmark's standard harness counts.
Categories
Where it counts
- Science — secondary, weight 0.35
Top 5
Current top scores
- GPT-6 Astra · 53.153 · Oct 30, 2026
- Claude Opus 5.5 · 49.55 · Oct 30, 2026
- Claude Sonnet 5.5 · 49.099 · Oct 30, 2026
- Claude Fable 5.1 · 47.748 · Oct 30, 2026
- GPT-6.1 Sol · 46.396 · Oct 30, 2026
| Model | Score | Date | Kind |
|---|---|---|---|
| GPT-6 Astra | 53.153 | 2026-10-30 | snapshot |
| Claude Opus 5.5 | 49.55 | 2026-10-30 | snapshot |
| Claude Sonnet 5.5 | 49.099 | 2026-10-30 | snapshot |
| Claude Fable 5.1 | 47.748 | 2026-10-30 | snapshot |
| GPT-6.1 Sol | 46.396 | 2026-10-30 | snapshot |
| Gemini 4 Argon | 45.495 | 2026-10-30 | snapshot |
| Claude Opus 5 | 37.387 | 2026-10-30 | snapshot |
| Gemini 3.8 Flash | 36.486 | 2026-10-30 | snapshot |
| Muse Spark 1.3 | 36.036 | 2026-10-30 | snapshot |
| Claude Haiku 5.5 | 35.135 | 2026-10-30 | snapshot |
| Muse Wonder Full | 35.135 | 2026-10-30 | snapshot |
| GPT-5.6 Sol | 33.333 | 2026-10-30 | snapshot |
| Grok 4.6 | 30.631 | 2026-10-30 | snapshot |
| GPT-6 Sol | 30.18 | 2026-10-30 | snapshot |
| Muse Wonder | 27.477 | 2026-10-30 | snapshot |
| Grok 4.7 | 25.225 | 2026-10-30 | snapshot |
| Qwen3 8 Max | 23.874 | 2026-10-30 | snapshot |
| GLM 5.3 | 22.973 | 2026-10-30 | snapshot |
| Mimo V2.6 Flash | 21.622 | 2026-10-30 | snapshot |
| DeepSeek V4.1 Flash | 21.171 | 2026-10-30 | snapshot |
| Gemini 3.1 Pro Preview | 20.721 | 2026-10-30 | snapshot |
| GPT-6 Luna | 19.369 | 2026-10-30 | snapshot |
| Step 5 Preview | 18.468 | 2026-10-30 | snapshot |
| Mimo V2.6 Pro | 15.315 | 2026-10-30 | snapshot |
| GPT-5.6 Luna | 14.414 | 2026-10-30 | snapshot |
| Mistral Large 4 | 12.162 | 2026-10-30 | snapshot |
| Kimi K3.1 Pro | 26.126 | 2026-10-30 | snapshot |