About
This benchmark suite is designed and maintained by RISE of the University of Basel.
For more details, visit the GitHub repository.
Contact
This benchmark is the result of lots of contributions (see below).
You are welcome to join us! Check out our GitHub-Repository, especially our Contributing Guidelines.
Core development team and contact:
- Maximilian Hinderman
0000-0002-9337-4655
(maximilian dot hindermann at unibas dot ch) - Sorin Marti
0000-0002-9541-1202
(sorin dot marti at unibas dot ch)
Version Log
Current version of this frontend 0.4.0
| v0.1.0 | 2025-08-25 | Github, ZIP, TAR | Initial release. |
| v0.2.0 | 2025-08-31 | Github, ZIP, TAR | Added tests, fixed broken links, added global performance table. |
| v0.2.1 | 2025-09-10 | Github, ZIP, TAR | Added radar chart, Added library cards benchmark. |
| v0.2.2 | 2025-09-19 | Github, ZIP, TAR | |
| v0.3.0 | 2025-10-03 | Github, ZIP, TAR | |
| v0.3.1 | 2025-10-29 | Github, ZIP, TAR | Added openrouter and scicore support, added benchmarks, added 170 new test configurations. |
| v0.4.0 | 2025-12-08 | Github, ZIP, TAR | Overauled presentation system, externalized LLM functionality, added text and mixed benchmarks. |
Contributors
0009-0007-0430-0050
Maximilian Hindermann
Core Development, Domain Expert, Data curator, Annotator, Analyst, Engineer
