Meta-Eval/EvalHarness
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

thinking.yaml: swe_bench_verified_agentic entry (env + max_turns)

Browse Source 
Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
sora 2026-09-18 04:57:38 +00:00
parent 2a2335f842
commit ace38eaf76
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
evalharness/config/thinking.yaml
View File

@ -58,3 +58,9 @@ general_fc:
max_tokens: 4096 max_tokens: 4096
tau2_bench: tau2_bench:
max_tokens: 16384 max_tokens: 16384
swe_bench_verified_agentic:
max_tokens: 4096
temperature: 0.0
env: swe_agentic
max_turns: 250