{ "created": "2026-09-21T03:43:10.353447+00:00", "categories": [ { "n": 5200, "errors": 435, "category": "format_sensitivity", "model": "Haidass-C", "inference_finished": 4765, "context_overflow": 435, "overflow_prompt_tokens": { "min": 4107, "median": 6101, "max": 22039 } }, { "n": 240, "errors": 0, "category": "irrelevance", "model": "Haidass-C", "inference_finished": 240 }, { "n": 884, "errors": 114, "category": "live_irrelevance", "model": "Haidass-C", "inference_finished": 770, "context_overflow": 114, "overflow_prompt_tokens": { "min": 4094, "median": 5223.5, "max": 22108 } }, { "n": 1053, "errors": 381, "category": "live_multiple", "model": "Haidass-C", "inference_finished": 672, "context_overflow": 381, "overflow_prompt_tokens": { "min": 4094, "median": 5670, "max": 21505 } }, { "n": 16, "errors": 0, "category": "live_parallel", "model": "Haidass-C", "inference_finished": 16 }, { "n": 24, "errors": 8, "category": "live_parallel_multiple", "model": "Haidass-C", "inference_finished": 16, "context_overflow": 8, "overflow_prompt_tokens": { "min": 4489, "median": 5243.0, "max": 9078 } }, { "n": 16, "errors": 3, "category": "live_relevance", "model": "Haidass-C", "inference_finished": 13, "context_overflow": 3, "overflow_prompt_tokens": { "min": 4452, "median": 4937, "max": 6631 } }, { "n": 258, "errors": 0, "category": "live_simple", "model": "Haidass-C", "inference_finished": 258 }, { "n": 192, "errors": 192, "category": "memory_kv", "model": "Haidass-C", "context_overflow": 192, "overflow_prompt_tokens": { "min": 8567, "median": 8672.0, "max": 8753 } }, { "n": 192, "errors": 19, "category": "memory_rec_sum", "model": "Haidass-C", "inference_finished": 173, "context_overflow": 19, "overflow_prompt_tokens": { "min": 4096, "median": 4164, "max": 4307 } }, { "n": 192, "errors": 192, "category": "memory_vector", "model": "Haidass-C", "context_overflow": 192, "overflow_prompt_tokens": { "min": 7933, "median": 8038.0, "max": 8119 } }, { "n": 200, "errors": 200, "category": "multi_turn_base", "model": "Haidass-C", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10276, "median": 19383.0, "max": 28233 } }, { "n": 200, "errors": 200, "category": "multi_turn_long_context", "model": "Haidass-C", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10276, "median": 19383.0, "max": 28233 } }, { "n": 200, "errors": 200, "category": "multi_turn_miss_func", "model": "Haidass-C", "context_overflow": 200, "overflow_prompt_tokens": { "min": 8970, "median": 18314.5, "max": 27518 } }, { "n": 200, "errors": 200, "category": "multi_turn_miss_param", "model": "Haidass-C", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10274, "median": 19380.0, "max": 28120 } }, { "n": 200, "errors": 0, "category": "multiple", "model": "Haidass-C", "inference_finished": 200 }, { "n": 200, "errors": 0, "category": "parallel", "model": "Haidass-C", "inference_finished": 200 }, { "n": 200, "errors": 0, "category": "parallel_multiple", "model": "Haidass-C", "inference_finished": 200 }, { "n": 100, "errors": 0, "category": "simple_java", "model": "Haidass-C", "inference_finished": 100 }, { "n": 50, "errors": 0, "category": "simple_javascript", "model": "Haidass-C", "inference_finished": 50 }, { "n": 400, "errors": 0, "category": "simple_python", "model": "Haidass-C", "inference_finished": 400 }, { "n": 5200, "errors": 435, "category": "format_sensitivity", "model": "Haidass-E", "inference_finished": 4765, "context_overflow": 435, "overflow_prompt_tokens": { "min": 4107, "median": 6101, "max": 22039 } }, { "n": 240, "errors": 0, "category": "irrelevance", "model": "Haidass-E", "inference_finished": 240 }, { "n": 884, "errors": 114, "category": "live_irrelevance", "model": "Haidass-E", "inference_finished": 770, "context_overflow": 114, "overflow_prompt_tokens": { "min": 4094, "median": 5223.5, "max": 22108 } }, { "n": 1053, "errors": 381, "category": "live_multiple", "model": "Haidass-E", "inference_finished": 672, "context_overflow": 381, "overflow_prompt_tokens": { "min": 4094, "median": 5670, "max": 21505 } }, { "n": 16, "errors": 0, "category": "live_parallel", "model": "Haidass-E", "inference_finished": 16 }, { "n": 24, "errors": 8, "category": "live_parallel_multiple", "model": "Haidass-E", "inference_finished": 16, "context_overflow": 8, "overflow_prompt_tokens": { "min": 4489, "median": 5243.0, "max": 9078 } }, { "n": 16, "errors": 3, "category": "live_relevance", "model": "Haidass-E", "inference_finished": 13, "context_overflow": 3, "overflow_prompt_tokens": { "min": 4452, "median": 4937, "max": 6631 } }, { "n": 258, "errors": 0, "category": "live_simple", "model": "Haidass-E", "inference_finished": 258 }, { "n": 192, "errors": 192, "category": "memory_kv", "model": "Haidass-E", "context_overflow": 192, "overflow_prompt_tokens": { "min": 8567, "median": 8672.0, "max": 8753 } }, { "n": 192, "errors": 19, "category": "memory_rec_sum", "model": "Haidass-E", "inference_finished": 173, "context_overflow": 19, "overflow_prompt_tokens": { "min": 4096, "median": 4164, "max": 4305 } }, { "n": 192, "errors": 192, "category": "memory_vector", "model": "Haidass-E", "context_overflow": 192, "overflow_prompt_tokens": { "min": 7933, "median": 8038.0, "max": 8119 } }, { "n": 200, "errors": 200, "category": "multi_turn_base", "model": "Haidass-E", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10276, "median": 19383.0, "max": 28233 } }, { "n": 200, "errors": 200, "category": "multi_turn_long_context", "model": "Haidass-E", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10276, "median": 19383.0, "max": 28233 } }, { "n": 200, "errors": 200, "category": "multi_turn_miss_func", "model": "Haidass-E", "context_overflow": 200, "overflow_prompt_tokens": { "min": 8970, "median": 18314.5, "max": 27518 } }, { "n": 200, "errors": 200, "category": "multi_turn_miss_param", "model": "Haidass-E", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10274, "median": 19380.0, "max": 28120 } }, { "n": 200, "errors": 0, "category": "multiple", "model": "Haidass-E", "inference_finished": 200 }, { "n": 200, "errors": 0, "category": "parallel", "model": "Haidass-E", "inference_finished": 200 }, { "n": 200, "errors": 0, "category": "parallel_multiple", "model": "Haidass-E", "inference_finished": 200 }, { "n": 100, "errors": 0, "category": "simple_java", "model": "Haidass-E", "inference_finished": 100 }, { "n": 50, "errors": 0, "category": "simple_javascript", "model": "Haidass-E", "inference_finished": 50 }, { "n": 400, "errors": 0, "category": "simple_python", "model": "Haidass-E", "inference_finished": 400 }, { "n": 5200, "errors": 435, "category": "format_sensitivity", "model": "Haidass-F", "inference_finished": 4765, "context_overflow": 435, "overflow_prompt_tokens": { "min": 4107, "median": 6101, "max": 22039 } }, { "n": 240, "errors": 0, "category": "irrelevance", "model": "Haidass-F", "inference_finished": 240 }, { "n": 884, "errors": 114, "category": "live_irrelevance", "model": "Haidass-F", "inference_finished": 770, "context_overflow": 114, "overflow_prompt_tokens": { "min": 4094, "median": 5223.5, "max": 22108 } }, { "n": 1053, "errors": 381, "category": "live_multiple", "model": "Haidass-F", "inference_finished": 672, "context_overflow": 381, "overflow_prompt_tokens": { "min": 4094, "median": 5670, "max": 21505 } }, { "n": 16, "errors": 0, "category": "live_parallel", "model": "Haidass-F", "inference_finished": 16 }, { "n": 24, "errors": 8, "category": "live_parallel_multiple", "model": "Haidass-F", "inference_finished": 16, "context_overflow": 8, "overflow_prompt_tokens": { "min": 4489, "median": 5243.0, "max": 9078 } }, { "n": 16, "errors": 3, "category": "live_relevance", "model": "Haidass-F", "inference_finished": 13, "context_overflow": 3, "overflow_prompt_tokens": { "min": 4452, "median": 4937, "max": 6631 } }, { "n": 258, "errors": 0, "category": "live_simple", "model": "Haidass-F", "inference_finished": 258 }, { "n": 192, "errors": 192, "category": "memory_kv", "model": "Haidass-F", "context_overflow": 192, "overflow_prompt_tokens": { "min": 8567, "median": 8672.0, "max": 8753 } }, { "n": 192, "errors": 19, "category": "memory_rec_sum", "model": "Haidass-F", "inference_finished": 173, "context_overflow": 19, "overflow_prompt_tokens": { "min": 4094, "median": 4164, "max": 4331 } }, { "n": 192, "errors": 192, "category": "memory_vector", "model": "Haidass-F", "context_overflow": 192, "overflow_prompt_tokens": { "min": 7933, "median": 8038.0, "max": 8119 } }, { "n": 200, "errors": 200, "category": "multi_turn_base", "model": "Haidass-F", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10276, "median": 19383.0, "max": 28233 } }, { "n": 200, "errors": 200, "category": "multi_turn_long_context", "model": "Haidass-F", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10276, "median": 19383.0, "max": 28233 } }, { "n": 200, "errors": 200, "category": "multi_turn_miss_func", "model": "Haidass-F", "context_overflow": 200, "overflow_prompt_tokens": { "min": 8970, "median": 18314.5, "max": 27518 } }, { "n": 200, "errors": 200, "category": "multi_turn_miss_param", "model": "Haidass-F", "context_overflow": 200, "overflow_prompt_tokens": { "min": 10274, "median": 19380.0, "max": 28120 } }, { "n": 200, "errors": 0, "category": "multiple", "model": "Haidass-F", "inference_finished": 200 }, { "n": 200, "errors": 0, "category": "parallel", "model": "Haidass-F", "inference_finished": 200 }, { "n": 200, "errors": 0, "category": "parallel_multiple", "model": "Haidass-F", "inference_finished": 200 }, { "n": 100, "errors": 0, "category": "simple_java", "model": "Haidass-F", "inference_finished": 100 }, { "n": 50, "errors": 0, "category": "simple_javascript", "model": "Haidass-F", "inference_finished": 50 }, { "n": 400, "errors": 0, "category": "simple_python", "model": "Haidass-F", "inference_finished": 400 } ], "warning": "Official scores are preserved. Context failures are not evidence of task reasoning performance on readable inputs. No overall score is valid while required categories are missing." }