add test results for gpt-oss-120b (high) to polyglot leaderboard

This commit is contained in:
oct4pie
2025-08-05 23:33:06 -07:00
committed by GitHub
parent 1af0e59149
commit ac40a4c5cb

View File

@@ -1682,4 +1682,32 @@
date: 2025-07-17
versions: 0.85.3.dev
seconds_per_case: 67.6
total_cost: 1.2357
total_cost: 1.2357
- dirname: 2025-08-06-04-54-48--gpt-oss-120b-high-polyglot
test_cases: 225
model: openrouter/openai/gpt-oss-120b
edit_format: diff
commit_hash: 1af0e59
pass_rate_1: 13.8
pass_rate_2: 41.8
pass_num_1: 31
pass_num_2: 94
percent_cases_well_formed: 79.1
error_outputs: 95
num_malformed_responses: 77
num_with_malformed_responses: 47
user_asks: 142
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
prompt_tokens: 3123768
completion_tokens: 856495
test_timeouts: 4
total_tests: 225
command: aider --model openrouter/openai/gpt-oss-120b
date: 2025-08-06
versions: 0.85.3.dev
seconds_per_case: 35.5
total_cost: 0.7406