- Giants
- Artificial Analysis
- SWE-Atlas QnA-AA Benchmark
SWE-Atlas QnA-AA Benchmark
Artificial Analysis's benchmark bar chart drew 6.5K views on X: 0.2x its typical post and #149 of 202 Artificial Analysis charts we track by views. Read Oct 27, 2026.
SWE-Atlas-QnA grading is revised, now SWE-Atlas-QnA-AA. Scale AI's 124 repository Q&A tasks are unchanged. We reworded 127 of the 1,306 rubric criteria for more consistent verdicts and moved to GPT-6 Luna (xhigh) as the judge, with five vot
Why it spread
It spread mainly because of launch timing and a big source: the post came from @ArtificialAnlys, whose reach sits in the top quarter, and it drew 5,860 views and 22 likes against the account's typical 19 likes, while reposts, quotes and saves stayed low at 0, 0 and 2.
What worked
- The post led with a concrete revision story: 127 of the 1,306 rubric criteria were reworded and the judge moved to GPT-6 Luna with five votes per criterion.
- It kept the task base stable and said so plainly, noting that Scale AI's 124 repository Q&A tasks are unchanged, which made the benchmark update easy to trust.
- It paired the announcement with a benchmark bar chart comparing models on SWE-Atlas QnA-AA, giving readers a visual result to react to.
What to borrow
We could frame our own chart posts as a clear before and after update, state exactly what changed and what stayed fixed, and attach a simple benchmark bar chart so the numbers are visible at a glance.
Careful
Do not over-read the engagement: reposts, quotes and saves were minimal, the design polish and self labelling were low, and the spread looks driven by the source's reach and timing rather than by the chart itself.
Written by our analysis model from the measured numbers above, not by Artificial Analysis.
Make it yours
We have not read this chart's numbers yet
Its own maker appears here once its numbers are read. Until then, these are other real charts in a similar format: each data page starts from that chart's numbers and takes yours.
API
Not in the API yet
We have not read this chart's numbers yet, so the API has nothing to return for it. Charts with numbers read are on the data page, and each one can be called by id.
More from Artificial Analysis
All 202
Other giants using a benchmark bar chart
All 189
Questions people ask
How far did Artificial Analysis's "SWE-Atlas QnA-AA Benchmark" chart travel?
6,517 views, 25 likes, 0 reposts and 3 saves on X, read Oct 27, 2026. A normal post from @ArtificialAnlys gets about 32.6K views.
What kind of chart is it?
A benchmark bar chart. Benchmark scores for various AI models on SWE-Atlas QnA-AA.
Can I use Artificial Analysis's chart?
Use the format, not the picture. The chart, logo and design belong to Artificial Analysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.