feat: add polyglot leaderboard entries for grok3 and optimus alpha

This commit is contained in:
Paul Gauthier 2025-04-11 07:17:56 +12:00 committed by Paul Gauthier (aider)
parent 43d4b21b23
commit 1d0167bbf4

View file

@ -909,4 +909,82 @@
date: 2025-04-06
versions: 0.81.2.dev
seconds_per_case: 20.5
total_cost: 0.0000
- dirname: 2025-04-10-04-21-31--grok3-diff-exuser
test_cases: 225
model: Grok 3 Beta
edit_format: diff
commit_hash: 2dd40fc-dirty
pass_rate_1: 22.2
pass_rate_2: 53.3
pass_num_1: 50
pass_num_2: 120
percent_cases_well_formed: 99.6
error_outputs: 1
num_malformed_responses: 1
num_with_malformed_responses: 1
user_asks: 68
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
total_tests: 225
command: aider --model openrouter/x-ai/grok-3-beta
date: 2025-04-10
versions: 0.81.2.dev
seconds_per_case: 15.3
total_cost: 11.0338
- dirname: 2025-04-10-18-47-24--grok3-mini-whole-exuser
test_cases: 225
model: Grok 3 Mini Beta
edit_format: whole
commit_hash: 14ffe77-dirty
pass_rate_1: 11.1
pass_rate_2: 34.7
pass_num_1: 25
pass_num_2: 78
percent_cases_well_formed: 100.0
error_outputs: 3
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 73
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 5
total_tests: 225
command: aider --model openrouter/x-ai/grok-3-mini-beta
date: 2025-04-10
versions: 0.81.2.dev
seconds_per_case: 35.1
total_cost: 0.7856
- dirname: 2025-04-10-19-02-44--oalpha-diff-exsys
test_cases: 225
model: Optimus Alpha
edit_format: diff
commit_hash: 532bc45-dirty
pass_rate_1: 21.3
pass_rate_2: 52.9
pass_num_1: 48
pass_num_2: 119
percent_cases_well_formed: 97.3
error_outputs: 7
num_malformed_responses: 6
num_with_malformed_responses: 6
user_asks: 182
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
total_tests: 225
command: aider --model openrouter/openrouter/optimus-alpha
date: 2025-04-10
versions: 0.81.2.dev
seconds_per_case: 18.4
total_cost: 0.0000