live
weekly refresh
basedagi.org
benchmark evidence

SWE Atlas - Codebase QnA

SWE Atlas - Codebase QnA public leaderboard from Scale Labs.

winner on SWE Atlas - Codebase QnA
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1Anthropic: Claude Opus 4.6
Anthropic
33.3
model-only
independent_benchmark
2000-01-01
2Anthropic: Claude Sonnet 4.6
Anthropic
31.2
model-only
independent_benchmark
2000-01-01
what this result means

SWE Atlas - Codebase QnA public leaderboard from Scale Labs.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on SWE Atlas - Codebase QnA. Broad task pages require independent corroboration before naming a general winner.

source record
category: agentic
metric: accuracy
matched models: 2
latest source date: 2000-01-01
direction: higher is better
inspect upstream source ->