Added 6 rows for chat model results (lite + turbo, fixture + derived) to benchmarks/model_benchmarks.csv.
14 lines
1.2 KiB
CSV
14 lines
1.2 KiB
CSV
date,script,model,mode,gate_status,turns,answered,caps,tool_turns,emitted,executed,contract,wall_s,contract_denom,executed_denom,tool_turns_denom,extra1_col,extra1_val,extra2_col,extra2_val
|
|
2026-09-06,summary,lite,quality,FAIL,8,8,0,0,0,0,58,26.9,58,0,8,coherence,4.0/5,hallucinations,4/8
|
|
2026-09-06,summary,lite,quality,FAIL,8,8,0,0,0,0,53,25.4,53,0,8,coherence,4.0/5,hallucinations,5/8
|
|
2026-09-06,embed,embed,dimension,PASS,1,1,0,0,0,0,1,0.1,1,0,1,actual_dim,768,expected_dim,768
|
|
2026-09-06,embed,embed,cosine,PASS,1,1,0,0,0,0,1,0.2,1,0,1,margin,0.283,quality,56
|
|
2026-09-06,embed,embed,speed,PASS,1,1,0,0,0,0,1,0.5,1,0,1,rate,93.8 vec/s,bad_vectors,0
|
|
2026-09-06,summary,turbo,quality,FAIL,8,8,0,0,0,0,63,25.3,63,0,8,coherence,4.0/5,hallucinations,3/8
|
|
2026-09-06,chat,lite,fixture,PASS,10,10,0,9,9,9,11,40.4,12,12,10,,,,
|
|
2026-09-06,chat,lite,fixture,PASS,10,10,0,10,9,9,13,40.5,14,14,10,,,,
|
|
2026-09-06,chat,lite,derived,FAIL,10,10,0,10,5,5,10,38.3,14,14,10,,,,
|
|
2026-09-06,chat,turbo,fixture,PASS,10,10,0,7,9,9,9,113.7,9,9,10,,,,
|
|
2026-09-06,chat,turbo,fixture,PASS,10,10,0,7,7,7,7,112.8,7,7,10,,,,
|
|
2026-09-06,chat,turbo,derived,FAIL,10,10,0,5,5,5,5,97.2,5,5,10,,,,
|