← The AI Systems Map
L0 · LabsBenchmark / eval

SWE-bench / Evaluation Benchmarks

Benchmarks that steer capital and marketing

SWE-bench, GPQA, MMLU, ARC-AGI, and LMArena are the scoreboards that drive model selection, enterprise procurement, and billions in narrative-driven valuation. Benchmark leadership is a marketing chokepoint, which also creates incentives for contamination and gaming.

Examples

SWE-bench, ARC-AGI, GPQA

How it fits the stack

SWE-bench / Evaluation Benchmarks with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

used bySWE-bench / EvaluationBenchmarksLabsAnthropic
SWE-bench / Evaluation BenchmarksFeeds ↓

SWE-bench / Evaluation Benchmarks in the AI stack. SWE-bench / Evaluation Benchmarks with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 2 entities, 1 relationships
  • Anthropicused bySWE-bench / Evaluation Benchmarks