change
229 review items still need manual judgment
The product keeps parser and mapping ambiguity visible instead of silently guessing.
Why this ranking changed
Every movement has a cause label.
Ranking movement is explained as source update, parser diff, mapping change, freshness decay, or new benchmark coverage.
source update / parser diff / mapping change
Arena moved via real benchmark movement
80 benchmark rows were added, 4 removed, and 16276 existing rows changed value or evaluation date. Window: 2026-06-20T23:37:10Z -> 2026-06-24T03:37:55Z.
source update / parser diff
Artificial Analysis moved via real benchmark movement
0 benchmark rows were added, 1 removed, and 1 existing rows changed value or evaluation date. Window: 2026-08-19T04:01:26Z -> 2026-08-19T04:03:57Z.
new benchmark coverage
BridgeBench moved via new benchmark coverage
10 benchmark rows were added, 10 removed, and 0 existing rows changed value or evaluation date. Window: 2026-05-15T16:26:59Z -> 2026-05-15T16:34:46Z.
parser diff / mapping change / new benchmark coverage
LiveBench moved via new benchmark coverage
651 benchmark rows were added, 0 removed, and 0 existing rows changed value or evaluation date. Window: 2026-08-19T04:01:41Z -> 2026-08-19T04:04:19Z.
change
Initial comparison-table release
Added comparison-table homepage, same-test normalization, per-cell source links, source pages, and custom-ranking preview.
change
Methodology contract published
Documented comparability rules, raw-vs-normalized behavior, and why unlike metrics are never averaged by default.
change
Artificial Analysis ID rule adopted
Stable model and creator IDs are now the preferred external identity keys when available.