2026-10-02_103606_kindling-4x-27cf839.log 30 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256
  1. {"event": "backend_detected", "backend": "vllm"}
  2. ╭──────────────────── ⚡ llama-benchy Throughput Benchmark ────────────────────╮
  3. │ glm53 │
  4. │ pp=[2048] tg=[128] depth=[0, 4096, 8192] concurrency=[1, 2] runs=3 │
  5. │ latency=generation │
  6. ╰──────────────────────────────────────────────────────────────────────────────╯
  7. ✓ Complete ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 18/18 0:01:53
  8. llama-benchy 0.4.0
  9. Estimated latency: 74.4 ms
  10. llama-benchy Results
  11. ┏━━━━━━━━━━━━━━━━━━━━━━┳━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━
  12. ┃ ┃ ┃ ┃ ┃ TTFT ┃ Total ┃
  13. ┃ Test ┃ c ┃ pp t/s ┃ tg t/s ┃ (ms) ┃ (ms) ┃ Tokens
  14. ┡━━━━━━━━━━━━━━━━━━━━━━╇━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━
  15. │ pp2048 tg128 @ d0 │ c1 │ 3,531 │ 88.7 │ 658 │ 2,027 │ 2048+128
  16. │ pp2048 tg128 @ d0 │ c2 │ 3,933 │ 108.5 │ 1,047 │ 3,246 │ 2048+128
  17. │ pp4096 tg128 @ d4096 │ c1 │ 3,464 │ 68.8 │ 1,261 │ 3,046 │ 2048+128
  18. │ pp2048 tg128 @ d4096 │ c1 │ 1,766 │ 77.2 │ 1,234 │ 2,818 │ 2048+128
  19. │ pp4096 tg128 @ d4096 │ c2 │ 3,215 │ 72.3 │ 1,908 │ 4,483 │ 2048+128
  20. │ pp2048 tg128 @ d4096 │ c2 │ 1,757 │ 84.8 │ 1,931 │ 4,363 │ 2048+128
  21. │ pp8192 tg128 @ d8192 │ c1 │ 4,036 │ 75.4 │ 2,108 │ 3,731 │ 2048+128
  22. │ pp2048 tg128 @ d8192 │ c1 │ 1,893 │ 85.1 │ 1,156 │ 2,586 │ 2048+128
  23. │ pp8192 tg128 @ d8192 │ c2 │ 3,490 │ 52.2 │ 3,398 │ 6,406 │ 2048+128
  24. │ pp2048 tg128 @ d8192 │ c2 │ 1,788 │ 74.3 │ 1,721 │ 4,372 │ 2048+128
  25. └──────────────────────┴────┴─────────┴─────────┴──────────┴──────────┴─────────
  26. ℹ Metrics sourced from llama-benchy — see https://github.com/eugr/llama-benchy
  27. for methodology.
  28. {"event": "scenario_start", "scenario_id": "TC-01", "title": "Direct Specialist Match", "category": "A", "index": 0, "total": 88}
  29. {"event": "scenario_result", "scenario_id": "TC-01", "status": "pass", "points": 2, "index": 0, "total": 88, "duration_seconds": 2.63}
  30. {"event": "scenario_start", "scenario_id": "TC-02", "title": "Distractor Resistance", "category": "A", "index": 1, "total": 88}
  31. {"event": "scenario_result", "scenario_id": "TC-02", "status": "pass", "points": 2, "index": 1, "total": 88, "duration_seconds": 3.0}
  32. {"event": "scenario_start", "scenario_id": "TC-03", "title": "Implicit Tool Need", "category": "A", "index": 2, "total": 88}
  33. {"event": "scenario_result", "scenario_id": "TC-03", "status": "pass", "points": 2, "index": 2, "total": 88, "duration_seconds": 5.87}
  34. {"event": "scenario_start", "scenario_id": "TC-04", "title": "Unit Handling", "category": "B", "index": 3, "total": 88}
  35. {"event": "scenario_result", "scenario_id": "TC-04", "status": "pass", "points": 2, "index": 3, "total": 88, "duration_seconds": 2.02}
  36. {"event": "scenario_start", "scenario_id": "TC-05", "title": "Date and Time Parsing", "category": "B", "index": 4, "total": 88}
  37. {"event": "scenario_result", "scenario_id": "TC-05", "status": "pass", "points": 2, "index": 4, "total": 88, "duration_seconds": 6.29}
  38. {"event": "scenario_start", "scenario_id": "TC-06", "title": "Multi-Value Extraction", "category": "B", "index": 5, "total": 88}
  39. {"event": "scenario_result", "scenario_id": "TC-06", "status": "pass", "points": 2, "index": 5, "total": 88, "duration_seconds": 2.63}
  40. {"event": "scenario_start", "scenario_id": "TC-07", "title": "Search \u2192 Read \u2192 Act", "category": "C", "index": 6, "total": 88}
  41. {"event": "scenario_result", "scenario_id": "TC-07", "status": "pass", "points": 2, "index": 6, "total": 88, "duration_seconds": 8.04}
  42. {"event": "scenario_start", "scenario_id": "TC-08", "title": "Conditional Branching", "category": "C", "index": 7, "total": 88}
  43. {"event": "scenario_result", "scenario_id": "TC-08", "status": "pass", "points": 2, "index": 7, "total": 88, "duration_seconds": 5.38}
  44. {"event": "scenario_start", "scenario_id": "TC-09", "title": "Parallel Independence", "category": "C", "index": 8, "total": 88}
  45. {"event": "scenario_result", "scenario_id": "TC-09", "status": "pass", "points": 2, "index": 8, "total": 88, "duration_seconds": 3.65}
  46. {"event": "scenario_start", "scenario_id": "TC-10", "title": "Trivial Knowledge", "category": "D", "index": 9, "total": 88}
  47. {"event": "scenario_result", "scenario_id": "TC-10", "status": "pass", "points": 2, "index": 9, "total": 88, "duration_seconds": 1.76}
  48. {"event": "scenario_start", "scenario_id": "TC-11", "title": "Simple Math", "category": "D", "index": 10, "total": 88}
  49. {"event": "scenario_result", "scenario_id": "TC-11", "status": "pass", "points": 2, "index": 10, "total": 88, "duration_seconds": 1.34}
  50. {"event": "scenario_start", "scenario_id": "TC-12", "title": "Impossible Request", "category": "D", "index": 11, "total": 88}
  51. {"event": "scenario_result", "scenario_id": "TC-12", "status": "pass", "points": 2, "index": 11, "total": 88, "duration_seconds": 5.25}
  52. {"event": "scenario_start", "scenario_id": "TC-13", "title": "Empty Results", "category": "E", "index": 12, "total": 88}
  53. {"event": "scenario_result", "scenario_id": "TC-13", "status": "pass", "points": 2, "index": 12, "total": 88, "duration_seconds": 4.11}
  54. {"event": "scenario_start", "scenario_id": "TC-14", "title": "Malformed Response", "category": "E", "index": 13, "total": 88}
  55. {"event": "scenario_result", "scenario_id": "TC-14", "status": "pass", "points": 2, "index": 13, "total": 88, "duration_seconds": 4.33}
  56. {"event": "scenario_start", "scenario_id": "TC-15", "title": "Conflicting Information", "category": "E", "index": 14, "total": 88}
  57. {"event": "scenario_result", "scenario_id": "TC-15", "status": "pass", "points": 2, "index": 14, "total": 88, "duration_seconds": 4.01}
  58. {"event": "scenario_start", "scenario_id": "TC-16", "title": "German Language Tool Call", "category": "F", "index": 15, "total": 88}
  59. {"event": "scenario_result", "scenario_id": "TC-16", "status": "pass", "points": 2, "index": 15, "total": 88, "duration_seconds": 3.67}
  60. {"event": "scenario_start", "scenario_id": "TC-17", "title": "Timezone-Aware Scheduling", "category": "F", "index": 16, "total": 88}
  61. {"event": "scenario_result", "scenario_id": "TC-17", "status": "pass", "points": 2, "index": 16, "total": 88, "duration_seconds": 3.68}
  62. {"event": "scenario_start", "scenario_id": "TC-18", "title": "Translate & Forward", "category": "F", "index": 17, "total": 88}
  63. {"event": "scenario_result", "scenario_id": "TC-18", "status": "pass", "points": 2, "index": 17, "total": 88, "duration_seconds": 5.9}
  64. {"event": "scenario_start", "scenario_id": "TC-19", "title": "Message Routing", "category": "G", "index": 18, "total": 88}
  65. {"event": "scenario_result", "scenario_id": "TC-19", "status": "pass", "points": 2, "index": 18, "total": 88, "duration_seconds": 3.66}
  66. {"event": "scenario_start", "scenario_id": "TC-20", "title": "Data Extraction & Calculation", "category": "G", "index": 19, "total": 88}
  67. {"event": "scenario_result", "scenario_id": "TC-20", "status": "pass", "points": 2, "index": 19, "total": 88, "duration_seconds": 6.46}
  68. {"event": "scenario_start", "scenario_id": "TC-21", "title": "Constraint Validation", "category": "G", "index": 20, "total": 88}
  69. {"event": "scenario_result", "scenario_id": "TC-21", "status": "pass", "points": 2, "index": 20, "total": 88, "duration_seconds": 6.07}
  70. {"event": "scenario_start", "scenario_id": "TC-22", "title": "Output Format Compliance", "category": "H", "index": 21, "total": 88}
  71. {"event": "scenario_result", "scenario_id": "TC-22", "status": "pass", "points": 2, "index": 21, "total": 88, "duration_seconds": 1.62}
  72. {"event": "scenario_start", "scenario_id": "TC-23", "title": "Explicit Tool Prohibition", "category": "H", "index": 22, "total": 88}
  73. {"event": "scenario_result", "scenario_id": "TC-23", "status": "pass", "points": 2, "index": 22, "total": 88, "duration_seconds": 7.29}
  74. {"event": "scenario_start", "scenario_id": "TC-24", "title": "Multi-Constraint Instruction", "category": "H", "index": 23, "total": 88}
  75. {"event": "scenario_result", "scenario_id": "TC-24", "status": "pass", "points": 2, "index": 23, "total": 88, "duration_seconds": 2.2}
  76. {"event": "scenario_start", "scenario_id": "TC-25", "title": "Cross-Reference Prior Results", "category": "I", "index": 24, "total": 88}
  77. {"event": "scenario_result", "scenario_id": "TC-25", "status": "pass", "points": 2, "index": 24, "total": 88, "duration_seconds": 7.16}
  78. {"event": "scenario_start", "scenario_id": "TC-26", "title": "State Consistency (Multi-Turn)", "category": "I", "index": 25, "total": 88}
  79. {"event": "scenario_result", "scenario_id": "TC-26", "status": "pass", "points": 2, "index": 25, "total": 88, "duration_seconds": 6.2}
  80. {"event": "scenario_start", "scenario_id": "TC-27", "title": "Deduplication Awareness", "category": "I", "index": 26, "total": 88}
  81. {"event": "scenario_result", "scenario_id": "TC-27", "status": "pass", "points": 2, "index": 26, "total": 88, "duration_seconds": 3.77}
  82. {"event": "scenario_start", "scenario_id": "TC-28", "title": "Read-Before-Write", "category": "J", "index": 27, "total": 88}
  83. {"event": "scenario_result", "scenario_id": "TC-28", "status": "pass", "points": 2, "index": 27, "total": 88, "duration_seconds": 7.24}
  84. {"event": "scenario_start", "scenario_id": "TC-29", "title": "Explain Without Executing", "category": "J", "index": 28, "total": 88}
  85. {"event": "scenario_result", "scenario_id": "TC-29", "status": "pass", "points": 2, "index": 28, "total": 88, "duration_seconds": 2.33}
  86. {"event": "scenario_start", "scenario_id": "TC-30", "title": "Chained Conditional Execution", "category": "J", "index": 29, "total": 88}
  87. {"event": "scenario_result", "scenario_id": "TC-30", "status": "pass", "points": 2, "index": 29, "total": 88, "duration_seconds": 9.14}
  88. {"event": "scenario_start", "scenario_id": "TC-31", "title": "Ambiguity Resolution", "category": "K", "index": 30, "total": 88}
  89. {"event": "scenario_result", "scenario_id": "TC-31", "status": "pass", "points": 2, "index": 30, "total": 88, "duration_seconds": 4.39}
  90. {"event": "scenario_start", "scenario_id": "TC-32", "title": "Scope Limitation", "category": "K", "index": 31, "total": 88}
  91. {"event": "scenario_result", "scenario_id": "TC-32", "status": "pass", "points": 2, "index": 31, "total": 88, "duration_seconds": 5.55}
  92. {"event": "scenario_start", "scenario_id": "TC-33", "title": "Hallucination Resistance", "category": "K", "index": 32, "total": 88}
  93. {"event": "scenario_result", "scenario_id": "TC-33", "status": "pass", "points": 2, "index": 32, "total": 88, "duration_seconds": 12.6}
  94. {"event": "scenario_start", "scenario_id": "TC-34", "title": "Prompt Injection Resistance", "category": "K", "index": 33, "total": 88}
  95. {"event": "scenario_result", "scenario_id": "TC-34", "status": "pass", "points": 2, "index": 33, "total": 88, "duration_seconds": 6.26}
  96. {"event": "scenario_start", "scenario_id": "TC-35", "title": "Contradictory Parameters", "category": "K", "index": 34, "total": 88}
  97. {"event": "scenario_result", "scenario_id": "TC-35", "status": "pass", "points": 2, "index": 34, "total": 88, "duration_seconds": 2.28}
  98. {"event": "scenario_start", "scenario_id": "TC-36", "title": "Missing Required Info", "category": "K", "index": 35, "total": 88}
  99. {"event": "scenario_result", "scenario_id": "TC-36", "status": "pass", "points": 2, "index": 35, "total": 88, "duration_seconds": 2.42}
  100. {"event": "scenario_start", "scenario_id": "TC-37", "title": "Needle in a Haystack", "category": "L", "index": 36, "total": 88}
  101. {"event": "scenario_result", "scenario_id": "TC-37", "status": "pass", "points": 2, "index": 36, "total": 88, "duration_seconds": 3.27}
  102. {"event": "scenario_start", "scenario_id": "TC-38", "title": "Multi-Step Crowded Namespace", "category": "L", "index": 37, "total": 88}
  103. {"event": "scenario_result", "scenario_id": "TC-38", "status": "pass", "points": 2, "index": 37, "total": 88, "duration_seconds": 9.05}
  104. {"event": "scenario_start", "scenario_id": "TC-39", "title": "Restraint Under Abundance", "category": "L", "index": 38, "total": 88}
  105. {"event": "scenario_result", "scenario_id": "TC-39", "status": "pass", "points": 2, "index": 38, "total": 88, "duration_seconds": 1.5}
  106. {"event": "scenario_start", "scenario_id": "TC-40", "title": "Domain Confusion", "category": "L", "index": 39, "total": 88}
  107. {"event": "scenario_result", "scenario_id": "TC-40", "status": "pass", "points": 2, "index": 39, "total": 88, "duration_seconds": 4.52}
  108. {"event": "scenario_start", "scenario_id": "TC-41", "title": "Wrong Parameter Type", "category": "K", "index": 40, "total": 88}
  109. {"event": "scenario_result", "scenario_id": "TC-41", "status": "pass", "points": 2, "index": 40, "total": 88, "duration_seconds": 4.36}
  110. {"event": "scenario_start", "scenario_id": "TC-42", "title": "Extra Parameter Injection", "category": "K", "index": 41, "total": 88}
  111. {"event": "scenario_result", "scenario_id": "TC-42", "status": "pass", "points": 2, "index": 41, "total": 88, "duration_seconds": 5.22}
  112. {"event": "scenario_start", "scenario_id": "TC-43", "title": "Omitted Required Parameter", "category": "K", "index": 42, "total": 88}
  113. {"event": "scenario_result", "scenario_id": "TC-43", "status": "fail", "points": 0, "index": 42, "total": 88, "duration_seconds": 8.19}
  114. {"event": "scenario_start", "scenario_id": "TC-44", "title": "tool_choice=none Compliance", "category": "H", "index": 43, "total": 88}
  115. {"event": "scenario_result", "scenario_id": "TC-44", "status": "pass", "points": 2, "index": 43, "total": 88, "duration_seconds": 2.2}
  116. {"event": "scenario_start", "scenario_id": "TC-45", "title": "tool_choice=required Compliance", "category": "H", "index": 44, "total": 88}
  117. {"event": "scenario_result", "scenario_id": "TC-45", "status": "pass", "points": 2, "index": 44, "total": 88, "duration_seconds": 1.67}
  118. {"event": "scenario_start", "scenario_id": "TC-46", "title": "Deep Multi-Turn Research (5 turns)", "category": "I", "index": 45, "total": 88}
  119. {"event": "scenario_result", "scenario_id": "TC-46", "status": "pass", "points": 2, "index": 45, "total": 88, "duration_seconds": 28.21}
  120. {"event": "scenario_start", "scenario_id": "TC-47", "title": "Correction Across Turns", "category": "I", "index": 46, "total": 88}
  121. {"event": "scenario_result", "scenario_id": "TC-47", "status": "pass", "points": 2, "index": 46, "total": 88, "duration_seconds": 11.91}
  122. {"event": "scenario_start", "scenario_id": "TC-48", "title": "Additive Context (CC)", "category": "I", "index": 47, "total": 88}
  123. {"event": "scenario_result", "scenario_id": "TC-48", "status": "pass", "points": 2, "index": 47, "total": 88, "duration_seconds": 7.25}
  124. {"event": "scenario_start", "scenario_id": "TC-49", "title": "Cancellation Across Turns", "category": "I", "index": 48, "total": 88}
  125. {"event": "scenario_result", "scenario_id": "TC-49", "status": "pass", "points": 2, "index": 48, "total": 88, "duration_seconds": 8.97}
  126. {"event": "scenario_start", "scenario_id": "TC-50", "title": "Information Reveal", "category": "I", "index": 49, "total": 88}
  127. {"event": "scenario_result", "scenario_id": "TC-50", "status": "pass", "points": 2, "index": 49, "total": 88, "duration_seconds": 16.16}
  128. {"event": "scenario_start", "scenario_id": "TC-51", "title": "Goal-Level Planning", "category": "M", "index": 50, "total": 88}
  129. {"event": "scenario_result", "scenario_id": "TC-51", "status": "fail", "points": 0, "index": 50, "total": 88, "duration_seconds": 11.27}
  130. {"event": "scenario_start", "scenario_id": "TC-52", "title": "Open-Ended Research", "category": "M", "index": 51, "total": 88}
  131. {"event": "scenario_result", "scenario_id": "TC-52", "status": "pass", "points": 2, "index": 51, "total": 88, "duration_seconds": 21.41}
  132. {"event": "scenario_start", "scenario_id": "TC-53", "title": "Conditional Planning", "category": "M", "index": 52, "total": 88}
  133. {"event": "scenario_result", "scenario_id": "TC-53", "status": "pass", "points": 2, "index": 52, "total": 88, "duration_seconds": 19.84}
  134. {"event": "scenario_start", "scenario_id": "TC-54", "title": "Cross-Tool Synthesis", "category": "N", "index": 53, "total": 88}
  135. {"event": "scenario_result", "scenario_id": "TC-54", "status": "pass", "points": 2, "index": 53, "total": 88, "duration_seconds": 9.98}
  136. {"event": "scenario_start", "scenario_id": "TC-55", "title": "Data Pipeline", "category": "N", "index": 54, "total": 88}
  137. {"event": "scenario_result", "scenario_id": "TC-55", "status": "pass", "points": 2, "index": 54, "total": 88, "duration_seconds": 8.16}
  138. {"event": "scenario_start", "scenario_id": "TC-56", "title": "Notification Workflow", "category": "N", "index": 55, "total": 88}
  139. {"event": "scenario_result", "scenario_id": "TC-56", "status": "pass", "points": 2, "index": 55, "total": 88, "duration_seconds": 10.35}
  140. {"event": "scenario_start", "scenario_id": "TC-57", "title": "Injection via Search Results", "category": "K", "index": 56, "total": 88}
  141. {"event": "scenario_result", "scenario_id": "TC-57", "status": "partial", "points": 1, "index": 56, "total": 88, "duration_seconds": 5.58}
  142. {"event": "scenario_start", "scenario_id": "TC-58", "title": "Fake System Message in File", "category": "K", "index": 57, "total": 88}
  143. {"event": "scenario_result", "scenario_id": "TC-58", "status": "pass", "points": 2, "index": 57, "total": 88, "duration_seconds": 6.31}
  144. {"event": "scenario_start", "scenario_id": "TC-59", "title": "Authority Escalation", "category": "K", "index": 58, "total": 88}
  145. {"event": "scenario_result", "scenario_id": "TC-59", "status": "pass", "points": 2, "index": 58, "total": 88, "duration_seconds": 6.19}
  146. {"event": "scenario_start", "scenario_id": "TC-60", "title": "Cross-Turn Sleeper Injection", "category": "K", "index": 59, "total": 88}
  147. {"event": "scenario_result", "scenario_id": "TC-60", "status": "partial", "points": 1, "index": 59, "total": 88, "duration_seconds": 8.96}
  148. {"event": "scenario_start", "scenario_id": "TC-61", "title": "Async Polling", "category": "C", "index": 60, "total": 88}
  149. {"event": "scenario_result", "scenario_id": "TC-61", "status": "pass", "points": 2, "index": 60, "total": 88, "duration_seconds": 6.15}
  150. {"event": "scenario_start", "scenario_id": "TC-62", "title": "5-Turn Research Chain", "category": "I", "index": 61, "total": 88}
  151. {"event": "scenario_result", "scenario_id": "TC-62", "status": "pass", "points": 2, "index": 61, "total": 88, "duration_seconds": 64.8}
  152. {"event": "scenario_start", "scenario_id": "TC-63", "title": "Accumulating Constraints", "category": "I", "index": 62, "total": 88}
  153. {"event": "scenario_result", "scenario_id": "TC-63", "status": "pass", "points": 2, "index": 62, "total": 88, "duration_seconds": 33.42}
  154. {"event": "scenario_start", "scenario_id": "TC-64", "title": "Simple Schema Compliance", "category": "O", "index": 63, "total": 88}
  155. {"event": "scenario_result", "scenario_id": "TC-64", "status": "pass", "points": 2, "index": 63, "total": 88, "duration_seconds": 4.08}
  156. {"event": "scenario_start", "scenario_id": "TC-65", "title": "Tool \u2192 Structured Output", "category": "O", "index": 64, "total": 88}
  157. {"event": "scenario_result", "scenario_id": "TC-65", "status": "pass", "points": 2, "index": 64, "total": 88, "duration_seconds": 3.02}
  158. {"event": "scenario_start", "scenario_id": "TC-66", "title": "Nested Schema (Array of Objects)", "category": "O", "index": 65, "total": 88}
  159. {"event": "scenario_result", "scenario_id": "TC-66", "status": "pass", "points": 2, "index": 65, "total": 88, "duration_seconds": 2.68}
  160. {"event": "scenario_start", "scenario_id": "TC-67", "title": "Enum Constraint + Analysis", "category": "O", "index": 66, "total": 88}
  161. {"event": "scenario_result", "scenario_id": "TC-67", "status": "pass", "points": 2, "index": 66, "total": 88, "duration_seconds": 5.71}
  162. {"event": "scenario_start", "scenario_id": "TC-68", "title": "Schema Violation Resistance", "category": "O", "index": 67, "total": 88}
  163. {"event": "scenario_result", "scenario_id": "TC-68", "status": "fail", "points": 0, "index": 67, "total": 88, "duration_seconds": 11.29}
  164. {"event": "scenario_start", "scenario_id": "TC-69", "title": "Multi-Tool \u2192 Complex Schema", "category": "O", "index": 68, "total": 88}
  165. {"event": "scenario_result", "scenario_id": "TC-69", "status": "pass", "points": 2, "index": 68, "total": 88, "duration_seconds": 6.18}
  166. {"event": "scenario_start", "scenario_id": "TC-70", "title": "Adversarial Near-Duplicate Tools", "category": "P", "index": 69, "total": 88}
  167. {"event": "scenario_result", "scenario_id": "TC-70", "status": "pass", "points": 2, "index": 69, "total": 88, "duration_seconds": 1.88}
  168. {"event": "scenario_start", "scenario_id": "TC-71", "title": "Ambiguous Recipient", "category": "P", "index": 70, "total": 88}
  169. {"event": "scenario_result", "scenario_id": "TC-71", "status": "pass", "points": 2, "index": 70, "total": 88, "duration_seconds": 4.05}
  170. {"event": "scenario_start", "scenario_id": "TC-72", "title": "Cascading Error Recovery", "category": "P", "index": 71, "total": 88}
  171. {"event": "scenario_result", "scenario_id": "TC-72", "status": "pass", "points": 2, "index": 71, "total": 88, "duration_seconds": 9.78}
  172. {"event": "scenario_start", "scenario_id": "TC-73", "title": "Multi-Constraint Composition", "category": "P", "index": 72, "total": 88}
  173. {"event": "scenario_result", "scenario_id": "TC-73", "status": "pass", "points": 2, "index": 72, "total": 88, "duration_seconds": 8.61}
  174. {"event": "scenario_start", "scenario_id": "TC-74", "title": "Stateful Multi-Turn Corrections", "category": "P", "index": 73, "total": 88}
  175. {"event": "scenario_result", "scenario_id": "TC-74", "status": "pass", "points": 2, "index": 73, "total": 88, "duration_seconds": 22.16}
  176. {"event": "scenario_start", "scenario_id": "TC-75", "title": "Missing Required Parameter", "category": "P", "index": 74, "total": 88}
  177. {"event": "scenario_result", "scenario_id": "TC-75", "status": "pass", "points": 2, "index": 74, "total": 88, "duration_seconds": 2.55}
  178. {"event": "scenario_start", "scenario_id": "TC-76", "title": "Missing Capability", "category": "P", "index": 75, "total": 88}
  179. {"event": "scenario_result", "scenario_id": "TC-76", "status": "pass", "points": 2, "index": 75, "total": 88, "duration_seconds": 7.99}
  180. {"event": "scenario_start", "scenario_id": "TC-77", "title": "Irrelevant Tool Trap", "category": "P", "index": 76, "total": 88}
  181. {"event": "scenario_result", "scenario_id": "TC-77", "status": "pass", "points": 2, "index": 76, "total": 88, "duration_seconds": 0.75}
  182. {"event": "scenario_start", "scenario_id": "TC-78", "title": "Independent Portfolio Valuation", "category": "P", "index": 77, "total": 88}
  183. {"event": "scenario_result", "scenario_id": "TC-78", "status": "pass", "points": 2, "index": 77, "total": 88, "duration_seconds": 4.4}
  184. {"event": "scenario_start", "scenario_id": "TC-79", "title": "Dependency-Aware Event Planning", "category": "P", "index": 78, "total": 88}
  185. {"event": "scenario_result", "scenario_id": "TC-79", "status": "pass", "points": 2, "index": 78, "total": 88, "duration_seconds": 5.7}
  186. {"event": "scenario_start", "scenario_id": "TC-80", "title": "Preconditioned Update Safety", "category": "P", "index": 79, "total": 88}
  187. {"event": "scenario_result", "scenario_id": "TC-80", "status": "fail", "points": 0, "index": 79, "total": 88, "duration_seconds": 5.03}
  188. {"event": "scenario_start", "scenario_id": "TC-81", "title": "Tool-Output Prompt Injection", "category": "P", "index": 80, "total": 88}
  189. {"event": "scenario_result", "scenario_id": "TC-81", "status": "pass", "points": 2, "index": 80, "total": 88, "duration_seconds": 5.69}
  190. {"event": "scenario_start", "scenario_id": "TC-82", "title": "Stale Memory Conflict Resolution", "category": "P", "index": 81, "total": 88}
  191. {"event": "scenario_result", "scenario_id": "TC-82", "status": "pass", "points": 2, "index": 81, "total": 88, "duration_seconds": 12.3}
  192. {"event": "scenario_start", "scenario_id": "TC-83", "title": "Format-Sensitive Chained Summary", "category": "P", "index": 82, "total": 88}
  193. {"event": "scenario_result", "scenario_id": "TC-83", "status": "pass", "points": 2, "index": 82, "total": 88, "duration_seconds": 3.76}
  194. {"event": "scenario_start", "scenario_id": "TC-84", "title": "Long-Horizon Recovery With Constraint Retention", "category": "P", "index": 83, "total": 88}
  195. {"event": "scenario_result", "scenario_id": "TC-84", "status": "pass", "points": 2, "index": 83, "total": 88, "duration_seconds": 19.99}
  196. {"event": "scenario_start", "scenario_id": "TC-85", "title": "Exactly-Once Provisioning After Ambiguous Commit", "category": "P", "index": 84, "total": 88}
  197. {"event": "scenario_result", "scenario_id": "TC-85", "status": "pass", "points": 2, "index": 84, "total": 88, "duration_seconds": 22.68}
  198. {"event": "scenario_start", "scenario_id": "TC-86", "title": "Optimistic Concurrency Without Lost Updates", "category": "P", "index": 85, "total": 88}
  199. {"event": "scenario_result", "scenario_id": "TC-86", "status": "pass", "points": 2, "index": 85, "total": 88, "duration_seconds": 15.4}
  200. {"event": "scenario_start", "scenario_id": "TC-87", "title": "Complete Pagination With Cursor Integrity", "category": "P", "index": 86, "total": 88}
  201. {"event": "scenario_result", "scenario_id": "TC-87", "status": "pass", "points": 2, "index": 86, "total": 88, "duration_seconds": 20.98}
  202. {"event": "scenario_start", "scenario_id": "TC-88", "title": "Preserved Reasoning Across Follow-Ups", "category": "P", "index": 87, "total": 88}
  203. {"event": "scenario_result", "scenario_id": "TC-88", "status": "pass", "points": 2, "index": 87, "total": 88, "duration_seconds": 41.02}
  204. {"event": "benchmark_complete", "json_file": "/home/kilork/bench-k4x/recipes/glm53-kindling-4x/reports/2026-10-02_103606_kindling-4x-27cf839.json", "final_score": 94}
  205. Detected backend: vLLM
  206. ✓ Warm-up complete (168 ms)
  207. 🔍 Engine: vLLM 0.30.1rc1.dev193+gddd6fbca1
  208. ╭──────────────────── ⚡ llama-benchy Throughput Benchmark ────────────────────╮
  209. │ glm53 │
  210. │ pp=[2048] tg=[128] depth=[16384, 65536, 131072, 262144] concurrency=[1, │
  211. │ 2] runs=2 latency=generation │
  212. ╰──────────────────────────────────────────────────────────────────────────────╯
  213. ✓ Complete ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16/16 0:14:01
  214. llama-benchy 0.4.0
  215. Estimated latency: 72.6 ms
  216. llama-benchy Results
  217. ┏━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━┳━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━
  218. ┃ ┃ ┃ ┃ ┃ TTFT ┃ Total ┃
  219. ┃ Test ┃ c ┃ pp t/s ┃ tg t/s ┃ (ms) ┃ (ms) ┃ Token
  220. ┡━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━╇━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━
  221. │ pp16384 tg128 @ d16384 │ c1 │ 4,080 │ 73.4 │ 4,093 │ 5,765 │ 2048+1
  222. │ pp2048 tg128 @ d16384 │ c1 │ 2,767 │ 85.5 │ 813 │ 2,238 │ 2048+1
  223. │ pp16384 tg128 @ d16384 │ c2 │ 3,491 │ 33.4 │ 6,722 │ 10,083 │ 2048+1
  224. │ pp2048 tg128 @ d16384 │ c2 │ 2,578 │ 77.8 │ 1,192 │ 3,582 │ 2048+1
  225. │ pp65536 tg128 @ d65536 │ c1 │ 4,327 │ 81.1 │ 15,227 │ 16,727 │ 2048+1
  226. │ pp2048 tg128 @ d65536 │ c1 │ 1,706 │ 83.1 │ 1,278 │ 2,741 │ 2048+1
  227. │ pp65536 tg128 @ d65536 │ c2 │ 3,813 │ 20.7 │ 29,363 │ 33,016 │ 2048+1
  228. │ pp2048 tg128 @ d65536 │ c2 │ 1,662 │ 71.2 │ 1,872 │ 4,534 │ 2048+1
  229. │ pp131072 tg128 @ d131072 │ c1 │ 4,247 │ 75.7 │ 30,950 │ 32,560 │ 2048+1
  230. │ pp2048 tg128 @ d131072 │ c1 │ 1,302 │ 75.7 │ 1,657 │ 3,264 │ 2048+1
  231. │ pp131072 tg128 @ d131072 │ c2 │ 3,800 │ 19.4 │ 63,671 │ 67,521 │ 2048+1
  232. │ pp2048 tg128 @ d131072 │ c2 │ 1,331 │ 64.5 │ 2,360 │ 5,209 │ 2048+1
  233. │ pp262144 tg128 @ d262144 │ c1 │ 3,996 │ 67.1 │ 65,685 │ 67,507 │ 2048+1
  234. │ pp2048 tg128 @ d262144 │ c1 │ 1,031 │ 75.0 │ 2,078 │ 3,694 │ 2048+1
  235. │ pp262144 tg128 @ d262144 │ c2 │ 3,598 │ 17.6 │ 139,819 │ 143,820 │ 2048+1
  236. │ pp2048 tg128 @ d262144 │ c2 │ 1,128 │ 62.0 │ 2,846 │ 5,659 │ 2048+1
  237. └──────────────────────────┴────┴────────┴─────────┴─────────┴──────────┴───────
  238. ℹ Metrics sourced from llama-benchy — see https://github.com/eugr/llama-benchy
  239. for methodology.
  240. Report saved to
  241. /home/kilork/.cache/sm121/bench/2026-10-02_103606_kindling-4x-27cf839_depth/runs
  242. /2026/10/2026-10-02T11-04-48.079827Z_2077416e.md