Download evaluation/development-gpu.summary.json from karmx/TinyQuery-140M: direct link, hf CLI and curl.
- Browser
- Download file 34.3 kB
-
https://huggingface.co/karmx/TinyQuery-140M/resolve/main/evaluation/development-gpu.summary.json
- Command line
-
hf download hf://karmx/TinyQuery-140M/evaluation/development-gpu.summary.json
-
curl -L -o development-gpu.summary.json https://huggingface.co/karmx/TinyQuery-140M/resolve/main/evaluation/development-gpu.summary.json
34.3 kB
| { | |
| "examples": 192, | |
| "seconds": 6.547292470932007, | |
| "decoding": "raw greedy, no repair, no teacher fallback", | |
| "checkpoint_sha256": "9489b5cde69c11f64b3e7031182e8248aa83790f1ad4aeefbf99a4e5e152e692", | |
| "sql_metric": "Compile against the supplied schema, then compare results on two generated SQLite fixtures after dialect adaptation; not native MySQL/PostgreSQL execution.", | |
| "metrics": { | |
| "json_valid": { | |
| "correct": 192, | |
| "total": 192, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 192, | |
| "total": 192, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 192, | |
| "total": 192, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 192, | |
| "total": 192, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 188, | |
| "total": 192, | |
| "rate": 0.9791666666666666 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 125, | |
| "total": 128, | |
| "rate": 0.9765625 | |
| }, | |
| "success": { | |
| "correct": 188, | |
| "total": 192, | |
| "rate": 0.9791666666666666 | |
| } | |
| }, | |
| "groups": { | |
| "language:noisy_en": { | |
| "json_valid": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 31, | |
| "total": 31, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "backend:supabase": { | |
| "json_valid": { | |
| "correct": 92, | |
| "total": 92, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 92, | |
| "total": 92, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 92, | |
| "total": 92, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 92, | |
| "total": 92, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 90, | |
| "total": 92, | |
| "rate": 0.9782608695652174 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 64, | |
| "total": 66, | |
| "rate": 0.9696969696969697 | |
| }, | |
| "success": { | |
| "correct": 90, | |
| "total": 92, | |
| "rate": 0.9782608695652174 | |
| } | |
| }, | |
| "operation:missing_schema": { | |
| "json_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:project": { | |
| "json_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 6, | |
| "total": 7, | |
| "rate": 0.8571428571428571 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 6, | |
| "total": 7, | |
| "rate": 0.8571428571428571 | |
| }, | |
| "success": { | |
| "correct": 6, | |
| "total": 7, | |
| "rate": 0.8571428571428571 | |
| } | |
| }, | |
| "language:hinglish": { | |
| "json_valid": { | |
| "correct": 52, | |
| "total": 52, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 52, | |
| "total": 52, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 52, | |
| "total": 52, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 52, | |
| "total": 52, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 51, | |
| "total": 52, | |
| "rate": 0.9807692307692307 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 36, | |
| "total": 37, | |
| "rate": 0.972972972972973 | |
| }, | |
| "success": { | |
| "correct": 51, | |
| "total": 52, | |
| "rate": 0.9807692307692307 | |
| } | |
| }, | |
| "operation:count_eq": { | |
| "json_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "language:en": { | |
| "json_valid": { | |
| "correct": 44, | |
| "total": 44, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 44, | |
| "total": 44, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 44, | |
| "total": 44, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 44, | |
| "total": 44, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 42, | |
| "total": 44, | |
| "rate": 0.9545454545454546 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 30, | |
| "total": 31, | |
| "rate": 0.967741935483871 | |
| }, | |
| "success": { | |
| "correct": 42, | |
| "total": 44, | |
| "rate": 0.9545454545454546 | |
| } | |
| }, | |
| "operation:group_count": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:distinct": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:year": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:max": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:bottom": { | |
| "json_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:lt": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:avg": { | |
| "json_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:sum": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 4, | |
| "rate": 0.75 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 4, | |
| "rate": 0.75 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 4, | |
| "rate": 0.75 | |
| } | |
| }, | |
| "language:hi": { | |
| "json_valid": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 48, | |
| "total": 48, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 47, | |
| "total": 48, | |
| "rate": 0.9791666666666666 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 28, | |
| "total": 29, | |
| "rate": 0.9655172413793104 | |
| }, | |
| "success": { | |
| "correct": 47, | |
| "total": 48, | |
| "rate": 0.9791666666666666 | |
| } | |
| }, | |
| "operation:project_eq": { | |
| "json_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:not_null": { | |
| "json_valid": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:or": { | |
| "json_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:date_after": { | |
| "json_valid": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 10, | |
| "total": 10, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:top": { | |
| "json_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:having": { | |
| "json_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:min": { | |
| "json_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 5, | |
| "total": 5, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:gt": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "backend:mysql": { | |
| "json_valid": { | |
| "correct": 100, | |
| "total": 100, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 100, | |
| "total": 100, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 100, | |
| "total": 100, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 100, | |
| "total": 100, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 98, | |
| "total": 100, | |
| "rate": 0.98 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 61, | |
| "total": 62, | |
| "rate": 0.9838709677419355 | |
| }, | |
| "success": { | |
| "correct": 98, | |
| "total": 100, | |
| "rate": 0.98 | |
| } | |
| }, | |
| "operation:count": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:group_sum": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:between": { | |
| "json_valid": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 6, | |
| "total": 6, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:sort_asc": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:sort_desc": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:sql_error": { | |
| "json_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 8, | |
| "total": 9, | |
| "rate": 0.8888888888888888 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 8, | |
| "total": 9, | |
| "rate": 0.8888888888888888 | |
| } | |
| }, | |
| "operation:all": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 4, | |
| "rate": 0.75 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 4, | |
| "rate": 0.75 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 4, | |
| "rate": 0.75 | |
| } | |
| }, | |
| "operation:and": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:month": { | |
| "json_valid": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:join_filter": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:eq": { | |
| "json_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:list_tables": { | |
| "json_valid": { | |
| "correct": 12, | |
| "total": 12, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 12, | |
| "total": 12, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 12, | |
| "total": 12, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 12, | |
| "total": 12, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 12, | |
| "total": 12, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 12, | |
| "total": 12, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:gte": { | |
| "json_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:lte": { | |
| "json_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:describe": { | |
| "json_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 4, | |
| "total": 4, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:join": { | |
| "json_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 3, | |
| "total": 3, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:null": { | |
| "json_valid": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 2, | |
| "total": 2, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:contains": { | |
| "json_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| }, | |
| "success": { | |
| "correct": 1, | |
| "total": 1, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:search": { | |
| "json_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:ticket": { | |
| "json_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 9, | |
| "total": 9, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:weather": { | |
| "json_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| } | |
| }, | |
| "operation:read_file": { | |
| "json_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "action_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "tool_correct": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "arguments_exact": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 0, | |
| "total": 0, | |
| "rate": 0.0 | |
| }, | |
| "success": { | |
| "correct": 7, | |
| "total": 7, | |
| "rate": 1.0 | |
| } | |
| } | |
| }, | |
| "rescoring": "Same saved raw outputs, with explicit supplied-schema compilation; no generation or output repair." | |
| } |