diff options
Diffstat (limited to 'judge_validation/comparison_results.csv')
| -rw-r--r-- | judge_validation/comparison_results.csv | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/judge_validation/comparison_results.csv b/judge_validation/comparison_results.csv new file mode 100644 index 0000000..1f75b24 --- /dev/null +++ b/judge_validation/comparison_results.csv @@ -0,0 +1,16 @@ +judge_1,judge_2,blackbox_kappa,glassbox_kappa,sophistication_kappa,n
+claude-sonnet-4-6,gpt-5-mini-2025-08-07,N/A,N/A,N/A,18
+claude-sonnet-4-6,gpt-4.1-mini,N/A,N/A,N/A,18
+claude-sonnet-4-6,claude-haiku-4-5-20251001,0.629,1.000,N/A,18
+claude-sonnet-4-6,grok-4-1-fast-reasoning,N/A,N/A,N/A,18
+claude-sonnet-4-6,grok-4-1-fast-non-reasoning,N/A,N/A,N/A,18
+gpt-5-mini-2025-08-07,gpt-4.1-mini,nan,nan,N/A,18
+gpt-5-mini-2025-08-07,claude-haiku-4-5-20251001,N/A,N/A,N/A,18
+gpt-5-mini-2025-08-07,grok-4-1-fast-reasoning,nan,nan,N/A,18
+gpt-5-mini-2025-08-07,grok-4-1-fast-non-reasoning,nan,nan,N/A,18
+gpt-4.1-mini,claude-haiku-4-5-20251001,N/A,N/A,N/A,18
+gpt-4.1-mini,grok-4-1-fast-reasoning,nan,nan,N/A,18
+gpt-4.1-mini,grok-4-1-fast-non-reasoning,nan,nan,N/A,18
+claude-haiku-4-5-20251001,grok-4-1-fast-reasoning,N/A,N/A,N/A,18
+claude-haiku-4-5-20251001,grok-4-1-fast-non-reasoning,N/A,N/A,N/A,18
+grok-4-1-fast-reasoning,grok-4-1-fast-non-reasoning,nan,nan,N/A,18
|
