RomanNum3ral
/
cai
mirror of https://github.com/aliasrobotics/cai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix cti-bench

This commit is contained in:
Mery-Sanz 2025-05-09 15:25:26 +02:00
parent 5d02f0c381
commit 99eaf4c1e6
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
benchmarks/dataset_cti_bench Submodule

@ -0,0 +1 @@
Subproject commit a801d31c6f1e8e279dfcf41f7fd4a16b72333046

2
ci/benchmarks/.benchmarks.yml
View File

@ -70,7 +70,7 @@ benchmarks-test-cti_bench-openrouter:
<<: *run_benchmarks
variables:
MODEL_NAME: "openrouter/qwen/qwen3-32b:free"
BENCHMARK_FILE: "benchmarks/cti_bench/data/cti-mcq1.tsv"
BENCHMARK_FILE: "benchmarks/dataset_cti_bench/cti-mcq1.tsv"
BENCHMARK_NAME: "cti_bench"
BACKEND: "openrouter"