<@U09DMU3EM2T> <@U08H0CRU1V4> is this swe-bench-m ...
# proj-agentl
limited-student-10747
04/06/2026, 4:30 PM@strong-ice-84145 @millions-crayon-32880 is this swe-bench-m result for claude code still broken? If so, maybe we can remove it from the index until we get a non-broken result? openhands-index-results/alternative_agents/claude_code/Claude-Opus-4.6/scores.json at main · OpenHands/openhands-index-results
👀 1
s
strong-ice-84145
04/06/2026, 4:50 PMAh indeed, I did fix the swebenchmultimodal issues but did not retrigger for claude opus 4.6 and sonnet 4.5.
I retriggered, updated results should be available in < 6 hours!
l
limited-student-10747
04/06/2026, 4:51 PMGreat, thanks!
a
average-processor-75195
05/13/2026, 1:25 PMNot sure where to post this, but I noticed on the OpenHands Index web page, the visualizations link for many results did not work for the swe-bench-results: https://laminar.sh/shared/evals/9464c828-db85-45f7-b4e9-b6526cb7d2f3
s
strong-ice-84145
05/13/2026, 1:32 PMInvestigating!
❤️ 1
strong-ice-84145
05/13/2026, 2:19 PMIssue with fix: https://github.com/OpenHands/openhands-index-results/issues/1117
@limited-student-10747 should I fix it? Or was it done in purpose?
l
limited-student-10747
05/13/2026, 2:29 PMIt should be fixed, thank you!
s
strong-ice-84145
05/13/2026, 3:00 PMThe first visualization on the website stills returns a 404 not found: https://laminar.sh/shared/evals/9464c828-db85-45f7-b4e9-b6526cb7d2f3
l
limited-student-10747
05/13/2026, 3:53 PMOh, sorry, I meant "we should fix this" 😅 I have not done anything yet, please go ahead
a
average-processor-75195
05/19/2026, 8:19 PMBump @strong-ice-84145 - not sure if you are working on it, but still not working
s
strong-ice-84145
05/19/2026, 9:47 PMWill fix it first thing tomorrow morning @average-processor-75195!
a
average-processor-75195
05/19/2026, 9:48 PMThank you ❤️
average-processor-75195
05/22/2026, 2:42 PMThanks for getting this working, I was using it last night
2 Views