{"schema":"every-benchmark-result/v1","benchmark":{"slug":"senior-engineer-benchmark","title":"Senior Engineer Benchmark"},"runs":[{"id":"muse-wonder-1.0__codex__high","model":"muse-wonder-1.0","agent":"codex","effort":"high","date":"2026-10-12","variant":null,"url":"https://checks.every.to/p/senior-engineer-benchmark/muse-wonder-1.0","avg":48,"tasks":{"04-proof-rewrite-integrated":48}},{"id":"gpt-6-astra__codex__high","model":"gpt-6-astra","agent":"codex","effort":"high","date":"2026-10-12","variant":null,"url":"https://checks.every.to/p/senior-engineer-benchmark/gpt-6-astra","avg":81,"tasks":{"04-proof-rewrite-integrated":81}},{"id":"claude-sonnet-5-5__claude__high","model":"claude-sonnet-5-5","agent":"claude","effort":"high","date":"2026-10-12","variant":null,"url":"https://checks.every.to/p/senior-engineer-benchmark/claude-sonnet-5-5","avg":85,"tasks":{"04-proof-rewrite-integrated":85}},{"id":"claude-opus-5-5__claude__high","model":"claude-opus-5-5","agent":"claude","effort":"high","date":"2026-10-12","variant":null,"url":"https://checks.every.to/p/senior-engineer-benchmark/claude-opus-5-5","avg":85,"tasks":{"04-proof-rewrite-integrated":85}},{"id":"gpt-6-sol__codex__high","model":"gpt-6-sol","agent":"codex","effort":"high","date":"2026-10-06","variant":null,"url":"https://checks.every.to/p/senior-engineer-benchmark/gpt-6-sol","avg":35,"tasks":{"04-proof-rewrite-integrated":35}},{"id":"gpt-6.1-sol__codex__high","model":"gpt-6.1-sol","agent":"codex","effort":"high","date":"2026-10-05","variant":null,"url":"https://checks.every.to/p/senior-engineer-benchmark/gpt-6.1-sol","avg":71,"tasks":{"04-proof-rewrite-integrated":71}}],"generated_at":"2026-10-13T02:58:07Z"}