aboutsummaryrefslogtreecommitdiff
path: root/benchmark/agbenchmark/__main__.py
AgeCommit message (Expand)AuthorFilesLines
2024-01-22feat(benchmark): Add `-N`, `--attempts` option for multiple attempts per chal...Gravatar Reinier van der Leer 1-0/+6
2024-01-16refactor(benchmark): Disable Helicone integrationsGravatar Reinier van der Leer 1-13/+13
2024-01-02AGBenchmark codebase clean-up (#6650)Gravatar Reinier van der Leer 1-209/+132
2023-10-02Fix benchmark ci (#5478)Gravatar merwanehamadi 1-1/+2
2023-10-02add load_dotenv (#5474)Gravatar merwanehamadi 1-0/+2
2023-09-20Make agbenchmark a proxy of the evaluated agent (#5279)Gravatar merwanehamadi 1-3/+0
2023-09-18Implement old polling mechanism (#5248)Gravatar merwanehamadi 1-49/+23
2023-09-17Refactor benchmark (#5247)Gravatar merwanehamadi 1-1/+6
2023-09-16Remove start from agbenchmark (#5241)Gravatar merwanehamadi 1-7/+2
2023-09-16Add ability to run multiple tests (#5233)Gravatar merwanehamadi 1-3/+2
2023-09-15Ability to run by categories (#5229)Gravatar merwanehamadi 1-2/+11
2023-09-15add benchmark endpoints mock (#5221)Gravatar merwanehamadi 1-0/+7
2023-09-13Support agent protocol in benchmark (#5213)Gravatar merwanehamadi 1-1/+1
2023-09-13Fix API Mode (#5209)Gravatar merwanehamadi 1-3/+2
2023-09-13fixed multiple report folder bugGravatar SwiftyOS 1-1/+51
2023-09-13Added ability to keep answersGravatar SwiftyOS 1-2/+9
2023-09-12Benchmark changesGravatar Merwane Hamadi 1-0/+254