data_analytics
Text-to-SQL analyst assistant
Convert questions into SQL and explain the query.
#1 Recommendation
gemini-3-pro-preview
Strong on FACTS Benchmark Suite facts_grounding_score_pct (88%) and FACTS Benchmark Suite facts_search_score_pct (100%)
external/google/gemini-3-pro-preview
19.9%
Score
26.0%
Confidence
Limited benchmark evidence for this use case.
63 ranked models with average evidence of 12.4 points. Rankings may shift as more benchmark data is ingested.
Ranked Models
30
Evidence Quality
80%
Scoring
Benchmark-backed
Top Signal
FACTS Benchmark Suite: facts_grounding_score_pct
All Ranked Models
Compare Models
Model A leads by +0.4%
Shareable Link →Model A
gemini-3-pro-preview
external/google/gemini-3-pro-preview
Rank #1
FACTS Benchmark Suite: facts_grounding_score_pct
Value 88.3% · Conf 100.0% · Weight 2.0%
facts_benchmark_suite.facts_grounding_score_pct (Mar 12, 2026)
FACTS Benchmark Suite: facts_search_score_pct
Value 100.0% · Conf 100.0% · Weight 1.7%
facts_benchmark_suite.facts_search_score_pct (Mar 12, 2026)
FACTS Benchmark Suite: average_score_pct
Value 100.0% · Conf 100.0% · Weight 1.6%
facts_benchmark_suite.average_score_pct (Mar 12, 2026)
Vals Finance Agent: overall_accuracy_pct
Value 87.0% · Conf 100.0% · Weight 1.6%
vals_finance_agent.overall_accuracy_pct (Mar 12, 2026)
Model B
gpt-4o-20241120
external/openai/gpt-4o-20241120
Rank #2
DuckDB NSQL Leaderboard: all_execution_accuracy
Value 96.2% · Conf 100.0% · Weight 7.0%
duckdb_nsql_leaderboard.all_execution_accuracy (Mar 12, 2026)
DuckDB NSQL Leaderboard: hard_execution_accuracy
Value 75.0% · Conf 100.0% · Weight 3.6%
duckdb_nsql_leaderboard.hard_execution_accuracy (Mar 12, 2026)
BIRD-CRITIC: success_rate_open_pct
Value 55.6% · Conf 100.0% · Weight 2.0%
bird_critic.success_rate_open_pct (Mar 12, 2026)
Spider2.0 Snow Text-to-SQL: snow_text_to_sql_score_pct
Value 13.5% · Conf 100.0% · Weight 0.7%
spider2_snow_text_to_sql.snow_text_to_sql_score_pct (Mar 12, 2026)
▶Ranking Diagnostics & Missing Models
Source Lift
Ranked
63
Sources
8
Quality
Insufficient
Vals CorpFin v2
vals_corp_fin_v2
40 rows
1.2% avg lift
Vals Legal Bench
vals_legal_bench
38 rows
0.3% avg lift
Vals Tax Eval v2
vals_tax_eval_v2
35 rows
0.3% avg lift
Vals MedQA
vals_medqa
34 rows
0.3% avg lift
Missing Strong Models
gpt-4.1-mini-20250414
external/openai/gpt-4-1-mini-20250414
Rank #31
13.1%
gpt-4o-2024-05-13
external/openai/gpt-4o-2024-05-13
Rank #51
10.5%
GPT-4.1-nano-2025-04-14
external/openai/gpt-4-1-nano-2025-04-14
Rank #89
6.4%
▶Taxonomy Details
Core Tasks
Required Modes
Domains
Related Use Cases
data_analytics
SQL debugging
Diagnose and fix SQL queries for correctness and performance.
Top: gpt-4o-20241120
data_analytics
Metric definition workshop
Turn ambiguous KPI definitions into precise, measurable specs.
Top: gpt-4o
data_analytics
Dashboard narratives
Generate weekly KPI narratives and investigation suggestions.
Top: gemini-3-pro-preview
data_analytics
Insight mining from text corpora
Extract themes and actions from large text datasets.
Top: qwen-2.5-72b-instruct