{ "context": { "cap_tokens": 162560, "max_model_len": 163840, "targets": [] }, "evaluation_protocol": { "budget_semantics": "visible_answer_tokens plus reasoning_headroom_tokens are sent as one max_tokens cap; the endpoint does not hard-partition the channels", "minimum_comparable_repetitions": 3, "minimum_pass_rate": 1.0, "reasoning_headroom_tokens": 0, "records_finish_reason": true, "records_full_visible_answer": true, "records_reasoning_channel_metadata": true, "repetitions": 3, "version": 3, "visible_answer_tokens": 256 }, "failures": [], "identity": { "base_url": "[private operator or asset text withheld]", "candidate_id": "reference-running", "config_id": "mtp3-160k", "engine": "ninfer", "gpu": "RTX5090", "model": "[private identity withheld]", "started_at": "2026-11-03T10:10:48Z" }, "intelligence": { "checks": [], "status": "not_run" }, "run_id": "fast-bakeoff-20261103T101048Z", "sampling": { "temperature": { "effective_request": 0.0, "requested": null, "sent": true }, "top_p": { "effective_request": null, "requested": null, "sent": false } }, "schema": "anvil-serving.fast-tier-bakeoff/v1", "score_inputs": { "e2e_p50_ms": null, "intelligence_pass_rate": null, "operational_fit_notes": [ "endpoint was already loaded; benchmark did not start or stop serves" ], "session_recall_passed": false, "thinking_mode": "unsupported", "tool_call_passed": false, "ttft_p50_ms": null, "usable_context_tokens": null, "voice_latency_ms": null }, "selection": { "context_targets": [ 32768 ], "endpoint_already_loaded": true, "requests_per_context": 1, "suites": [] }, "session": { "checks": [], "status": "not_run" }, "source_recipe": { "ref": null, "serve_command": null }, "suites": { "local-llm-coding-20261103": { "checks": [ { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 455, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 949.5001999894157, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 130, "prompt_tokens": 152, "total_tokens": 282 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 455, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 756.9827999686822, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 130, "prompt_tokens": 152, "total_tokens": 282 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 455, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 763.7737999903038, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 130, "prompt_tokens": 152, "total_tokens": 282 } } ], "id": "merge_intervals", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" }, { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1068, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1548.0035999789834, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 290, "prompt_tokens": 180, "total_tokens": 470 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1068, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1545.7999000209384, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 290, "prompt_tokens": 180, "total_tokens": 470 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1068, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1565.7516000210308, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 290, "prompt_tokens": 180, "total_tokens": 470 } } ], "id": "stable_toposort", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" }, { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1142, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1414.2304999986663, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 274, "prompt_tokens": 168, "total_tokens": 442 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1142, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1427.2461999789812, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 274, "prompt_tokens": 168, "total_tokens": 442 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1142, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1427.3261999478564, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 274, "prompt_tokens": 168, "total_tokens": 442 } } ], "id": "parse_csv_line", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" }, { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 938, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1306.75039999187, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 247, "prompt_tokens": 182, "total_tokens": 429 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 938, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1293.92349999398, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 247, "prompt_tokens": 182, "total_tokens": 429 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 938, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1292.8323000087403, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 247, "prompt_tokens": 182, "total_tokens": 429 } } ], "id": "apply_edits", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" }, { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 484, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 673.007300007157, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 123, "prompt_tokens": 162, "total_tokens": 285 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 484, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 691.4676000014879, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 123, "prompt_tokens": 162, "total_tokens": 285 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 484, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 685.6889000046067, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 123, "prompt_tokens": 162, "total_tokens": 285 } } ], "id": "normalize_posix_path", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" }, { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1330, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1777.617099985946, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 321, "prompt_tokens": 225, "total_tokens": 546 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1330, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1780.1602000254206, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 321, "prompt_tokens": 225, "total_tokens": 546 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1330, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1781.570399994962, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 321, "prompt_tokens": 225, "total_tokens": 546 } } ], "id": "lru_trace", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" }, { "attempt_count": 3, "attempts": [ { "attempt": 1, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1097, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1667.8702000062913, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 289, "prompt_tokens": 187, "total_tokens": 476 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1097, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1683.3948999992572, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 289, "prompt_tokens": 187, "total_tokens": 476 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 12288, "reasoning_headroom_tokens": 8192, "visible_answer_tokens": 4096 }, "content": "[text withheld]", "content_chars": 1097, "content_excerpt": "[text withheld]", "failure_class": null, "finish_reason": "stop", "latency_ms": 1667.6675000344403, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "text_checks": [ { "name": "marker", "passed": true } ], "usage": { "completion_tokens": 289, "prompt_tokens": 187, "total_tokens": 476 } } ], "id": "decode_uvarint", "pass_count": 3, "pass_rate": 1.0, "required_pass_rate": 1.0, "status": "passed", "validator": "deterministic_text_checks" } ], "date": "2026-11-03", "evidence_use": "diagnostic", "source": "[text withheld]", "source_sha256": "[private fingerprint withheld]", "status": "passed", "validator_strength": "deterministic_marker", "work_class": "bounded-pure-python-coding" } }, "thinking": { "chat_template_kwargs": null, "control_evidence": null, "control_evidence_sha256": null, "control_mechanism": "unsupported", "control_requested": null, "control_status": "unsupported", "force_nonempty_content": false, "mode": "unsupported", "reasoning_effort": null, "unsupported": true }, "timing": { "chat": { "completion_tokens_max": null, "completion_tokens_mean": null, "completion_tokens_mean_ci95_high": null, "completion_tokens_mean_ci95_low": null, "completion_tokens_min": null, "completion_tokens_p25": null, "completion_tokens_p50": null, "completion_tokens_p75": null, "completion_tokens_p90": null, "completion_tokens_p95": null, "completion_tokens_p99": null, "completion_tokens_samples": 0, "completion_tokens_stddev": null, "content_chunks": 0, "controlled_output_exact_adherence": 0, "controlled_output_exact_adherence_rate": null, "controlled_output_samples": 0, "controlled_output_unobservable": 0, "decode_tok_s_max": null, "decode_tok_s_mean": null, "decode_tok_s_mean_ci95_high": null, "decode_tok_s_mean_ci95_low": null, "decode_tok_s_min": null, "decode_tok_s_p25": null, "decode_tok_s_p50": null, "decode_tok_s_p75": null, "decode_tok_s_p90": null, "decode_tok_s_p95": null, "decode_tok_s_p99": null, "decode_tok_s_samples": 0, "decode_tok_s_stddev": null, "e2e_max_ms": null, "e2e_mean_ci95_high_ms": null, "e2e_mean_ci95_low_ms": null, "e2e_mean_ms": null, "e2e_min_ms": null, "e2e_p25_ms": null, "e2e_p50_ms": null, "e2e_p75_ms": null, "e2e_p90_ms": null, "e2e_p95_ms": null, "e2e_p99_ms": null, "e2e_samples": 0, "e2e_stddev_ms": null, "effective_prefill_tok_s_max": null, "effective_prefill_tok_s_mean": null, "effective_prefill_tok_s_mean_ci95_high": null, "effective_prefill_tok_s_mean_ci95_low": null, "effective_prefill_tok_s_min": null, "effective_prefill_tok_s_p25": null, "effective_prefill_tok_s_p50": null, "effective_prefill_tok_s_p75": null, "effective_prefill_tok_s_p90": null, "effective_prefill_tok_s_p95": null, "effective_prefill_tok_s_p99": null, "effective_prefill_tok_s_samples": 0, "effective_prefill_tok_s_stddev": null, "generation_max_ms": null, "generation_mean_ci95_high_ms": null, "generation_mean_ci95_low_ms": null, "generation_mean_ms": null, "generation_min_ms": null, "generation_p25_ms": null, "generation_p50_ms": null, "generation_p75_ms": null, "generation_p90_ms": null, "generation_p95_ms": null, "generation_p99_ms": null, "generation_samples": 0, "generation_stddev_ms": null, "mean_inter_token_latency_ms_max": null, "mean_inter_token_latency_ms_mean": null, "mean_inter_token_latency_ms_mean_ci95_high": null, "mean_inter_token_latency_ms_mean_ci95_low": null, "mean_inter_token_latency_ms_min": null, "mean_inter_token_latency_ms_p25": null, "mean_inter_token_latency_ms_p50": null, "mean_inter_token_latency_ms_p75": null, "mean_inter_token_latency_ms_p90": null, "mean_inter_token_latency_ms_p95": null, "mean_inter_token_latency_ms_p99": null, "mean_inter_token_latency_ms_samples": 0, "mean_inter_token_latency_ms_stddev": null, "mean_time_per_output_token_max_ms": null, "mean_time_per_output_token_mean_ci95_high_ms": null, "mean_time_per_output_token_mean_ci95_low_ms": null, "mean_time_per_output_token_mean_ms": null, "mean_time_per_output_token_min_ms": null, "mean_time_per_output_token_p25_ms": null, "mean_time_per_output_token_p50_ms": null, "mean_time_per_output_token_p75_ms": null, "mean_time_per_output_token_p90_ms": null, "mean_time_per_output_token_p95_ms": null, "mean_time_per_output_token_p99_ms": null, "mean_time_per_output_token_samples": 0, "mean_time_per_output_token_stddev_ms": null, "output_tokens": 0, "prompt_token_samples": 0, "prompt_tokens": null, "prompt_tokens_max": null, "prompt_tokens_mean": null, "prompt_tokens_mean_ci95_high": null, "prompt_tokens_mean_ci95_low": null, "prompt_tokens_min": null, "prompt_tokens_p25": null, "prompt_tokens_p50": null, "prompt_tokens_p75": null, "prompt_tokens_p90": null, "prompt_tokens_p95": null, "prompt_tokens_p99": null, "prompt_tokens_samples": 0, "prompt_tokens_stddev": null, "reasoning_chunks": 0, "request_canary_passed": 0, "request_canary_samples": 0, "time_to_first_output_max_ms": null, "time_to_first_output_mean_ci95_high_ms": null, "time_to_first_output_mean_ci95_low_ms": null, "time_to_first_output_mean_ms": null, "time_to_first_output_min_ms": null, "time_to_first_output_p25_ms": null, "time_to_first_output_p50_ms": null, "time_to_first_output_p75_ms": null, "time_to_first_output_p90_ms": null, "time_to_first_output_p95_ms": null, "time_to_first_output_p99_ms": null, "time_to_first_output_samples": 0, "time_to_first_output_stddev_ms": null, "tpot_max_ms": null, "tpot_mean_ci95_high_ms": null, "tpot_mean_ci95_low_ms": null, "tpot_mean_ms": null, "tpot_min_ms": null, "tpot_p25_ms": null, "tpot_p50_ms": null, "tpot_p75_ms": null, "tpot_p90_ms": null, "tpot_p95_ms": null, "tpot_p99_ms": null, "tpot_samples": 0, "tpot_stddev_ms": null, "ttft_max_ms": null, "ttft_mean_ci95_high_ms": null, "ttft_mean_ci95_low_ms": null, "ttft_mean_ms": null, "ttft_min_ms": null, "ttft_p25_ms": null, "ttft_p50_ms": null, "ttft_p75_ms": null, "ttft_p90_ms": null, "ttft_p95_ms": null, "ttft_p99_ms": null, "ttft_samples": 0, "ttft_stddev_ms": null }, "wall_ms": 27702.83019996714 }, "tool": { "checks": [], "status": "not_run" }, "voice": { "status": "not_run", "stt_latency_ms": null, "total_turn_latency_ms": null, "tts_latency_ms": null } }