Scoreboard
6 models1 task
| Model | Overall | proof-rewrite-integrated |
|---|---|---|
| claude-opus-5-5 Claude Code · high effort |
85% | 85% |
| claude-sonnet-5-5 Claude Code · high effort |
85% | 85% |
| gpt-6-astra Codex CLI · high effort |
81% | 81% |
| gpt-6.1-sol Codex CLI · high effort |
71% | 71% |
| muse-wonder-1.0 Codex CLI · high effort |
48% | 48% |
| gpt-6-sol Codex CLI · high effort |
35% | 35% |
How scores work
Senior Engineer Benchmark is one person's benchmark: real work they use AI for, scored by the things they check when deciding whether an output is good. It answers "which model is best at my job, for the things I care about", not a general claim about model quality.
One row per model, each case scored by its latest public run. Under each score a bar is ink for the share of checks passed and hatched for the rest; the best score in each column is bold.
A run reads as checks passed over checks applicable. Code checks are answered by a program, model checks by an LLM judge, which is always Claude. A case is scored by its latest run, a task is the mean of its cases, and Overall is the mean across tasks. Overall's bar is as long as the share of the tasks the model ran, and the rest of its track is empty. Open a cell to read the actual output beside the checks it passed and failed.