{ "model_id": "qwen2.5-0.5b", "provider_id": "local-ollama", "quality": null, "retain": { "timestamp": "2026-02-20T16:15:34.336134+00:00", "model_id": "qwen2.5-0.5b", "model_name": "qwen2.5:0.5b", "provider_id": "local-ollama", "size_gb": 0.0, "dataset": "locomo_3k", "concurrency": 1, "wall_s": 1180.2592420578003, "summary": { "success": 0, "total": 20, "wall_s": 1180.259, "avg_latency_s": null, "throughput_rps": null, "completion_toks_s": null, "total_toks_s": null, "out_in_ratio": null, "tokens_per_fact": null }, "tests": [ { "test_index": 1, "latency_s": 8.480972051620483, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"All messages have been successfully extracted.\",\n \"status\": \"success\"\n}" }, { "test_index": 2, "latency_s": 270.6438179016113, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"All messages are successfully extracted.\",\n \"status\": \"success\"\n}" }, { "test_index": 3, "latency_s": 10.189910173416138, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"status\": \"success\",\n \"message\": \"All data has been successfully extracted and processed.\",\n \"data\": {\n \"user\": {\n \"name\": \"Jon\",\n \"email\": \"jon@example.com\",\n \"phone_number\": " }, { "test_index": 4, "latency_s": 27.96056890487671, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"Jon\": {\n \"status\": \"working\",\n \"goals\": [\n \"expand dance studio's social media presence and offer workshops and classes to local schools and centers\",\n \"host a dance competition n" }, { "test_index": 5, "latency_s": 10.100296020507812, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"date\": \"2023-01-28\",\n \"events\": [\n {\n \"day\": \"9\",\n \"event\": \"attended a service-focused online group\",\n \"notes\": \"Everyone there is incredible with their own inspiring stories." }, { "test_index": 6, "latency_s": 135.6602909564972, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"Thank you for sharing your experiences with John and Maria. We appreciate your insights into their journey towards positive change.\",\n \"feedback\": [\n {\n \"sender\": \"John\",\n " }, { "test_index": 7, "latency_s": 5.31131911277771, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"The assistant successfully extracted the information from the provided text.\",\n \"status\": \"success\"\n}" }, { "test_index": 8, "latency_s": 2.548471689224243, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"The message has been successfully sent.\",\n \"status\": \"success\"\n}" }, { "test_index": 9, "latency_s": 12.44188904762268, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"messages\": [\n {\n \"sender\": \"John\",\n \"recipient\": \"Tim\",\n \"message\": \"Hey Tim! Long time no see! Been super busy lately. Guess what? Just skyped with that Harry Potter fan I met " }, { "test_index": 10, "latency_s": 3.058488130569458, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"The assistant successfully extracted the information from the provided text.\",\n \"status\": \"success\"\n}" }, { "test_index": 11, "latency_s": 361.33601784706116, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: exception: Request timed out." }, { "test_index": 12, "latency_s": 5.568586111068726, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"activities\": [\n {\n \"date\": \"2023-06-11\",\n \"location\": \"Rock Climbing Class\",\n \"description\": \"A great experience for climbing mountains, challenging but rewarding.\"\n },\n {" }, { "test_index": 13, "latency_s": 21.611713647842407, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"games_played\": [\n {\n \"game_name\": \"CS:GO\",\n \"date\": \"2022-03-15\",\n \"status\": \"completed\"\n },\n {\n \"game_name\": \"RPGs\",\n \"date\": \"2022-04-04\",\n \"status\": \"ong" }, { "test_index": 14, "latency_s": 10.368030786514282, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"user\": {\n \"name\": \"John\",\n \"age\": 30,\n \"interests\": [\"programming\", \"traveling\", \"coding\"],\n \"achievements\": [\n {\n \"date\": \"29 April, 2022\",\n \"achievement\": \"took o" }, { "test_index": 15, "latency_s": 244.7875621318817, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"All messages are received and processed successfully.\",\n \"status\": \"success\"\n}" }, { "test_index": 16, "latency_s": 9.742594003677368, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"deborah\": {\n \"jolene\": {\n \"time_management\": \"I use the Pomodoro Technique, working for 25 minutes and taking a 5-minute break every hour.\",\n \"exam_schedule\": \"I try to create a dail" }, { "test_index": 17, "latency_s": 2.187898874282837, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"All messages have been successfully extracted.\"\n}" }, { "test_index": 18, "latency_s": 26.71468186378479, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"messages\": [\n {\n \"sender\": \"Sam\",\n \"recipient\": \"Evan\",\n \"message\": \"Hey Evan! Exciting news: I started a new diet and exercise routine last Monday and it's made a huge differen" }, { "test_index": 19, "latency_s": 3.1076691150665283, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"All messages have been successfully extracted.\",\n \"status\": \"success\"\n}" }, { "test_index": 20, "latency_s": 8.346274137496948, "num_facts": 0, "valid_json": false, "success": false, "retries": 1, "prompt_tokens": 0, "completion_tokens": 0, "error": "attempt 1: missing_facts_key | raw: {\n \"message\": \"The message has been successfully extracted from the provided text.\",\n \"extracted_text\": \"Hey Dave, I had a lil car accident last Friday. The mechanic helped me get my car running aga" } ] } }