| ▲ | PunchTornado 5 hours ago | |
The biggest increase is LiveCodeBench Pro: 2887. The rest are in line with Opus 4.6 or slightly better or slightly worse. | ||
| ▲ | shmoogy 4 hours ago | parent [-] | |
but is it still terrible at tool calls in actual agentic flows? | ||
| ▲ | PunchTornado 5 hours ago | |
The biggest increase is LiveCodeBench Pro: 2887. The rest are in line with Opus 4.6 or slightly better or slightly worse. | ||
| ▲ | shmoogy 4 hours ago | parent [-] | |
but is it still terrible at tool calls in actual agentic flows? | ||