Claude Mythos Preview
Claude Mythos Preview from Anthropic.
Shogo Agent Index
UnrankedNot ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
86
estimated
Long-horizon autonomy
81
50% measured
Knowledge-work agents
65
estimated
Computer use
76
estimated
Security & context learning
65
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 92 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 98 | |
| DeepSWE | est. | 6% | predicted 88 | |
| FrontierSWE | est. | 5% | predicted 76 | |
| CursorBench | est. | 4% | predicted 61 | |
| GSO-Bench | est. | 4% | predicted 87 | |
| METR Time Horizons | 85.2% | 10% | source | |
| Vending-Bench 2 | est. | 6% | predicted 97 | |
| PostTrainBench | est. | 4% | predicted 45 | |
| APEX-Agents | est. | 8% | predicted 82 | |
| GDPval | est. | 7% | predicted 77 | |
| Remote Labor Index | est. | 5% | predicted 32 | |
| DeepResearch Bench | est. | 5% | predicted 54 | |
| OSWorld 2.0 | est. | 6% | predicted 61 | |
| OSWorld | est. | 4% | predicted 98 | |
| Cybench | est. | 5% | predicted 96 | |
| CL-bench | est. | 5% | predicted 34 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ExploitBench | Security & context | 73.8% | source |