BasedAGIBasedAGI
Menu
Rankings live

data_analytics

Best Text-to-SQL Model

Ranked text-to-SQL models for converting natural language questions into accurate SQL queries.

#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

23

Evidence

Runners-up:#2 gpt-4o-20241120 (19.5%)#3 gpt-4o (18.2%)#4 qwen-2.5-72b-instruct (17.9%)

Ranked Models

30

Evidence Quality

80%

Scoring

Benchmark-backed

Top Signal

FACTS Benchmark Suite: facts_grounding_score_pct

All Ranked Models

Max params:
Min confidence:
30 of 30
RankModelScore
#1gemini-3-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct (88%) and FACTS Benchmark Suite facts_search_score_pct (100%)

19.9%
#2gpt-4o-20241120

Strong on DuckDB NSQL Leaderboard all_execution_accuracy (96%) and DuckDB NSQL Leaderboard hard_execution_accuracy (75%)

19.5%
#4gpt-4o
18.2%
#5qwen-2.5-72b-instruct
17.9%
#6gemini-2.5-pro
17.4%
#7deepseek/deepseek-r1
16.4%
#8anthropic/claude-sonnet-4.6
15.0%
#9gpt-5-mini-2025-08-07
14.7%
#10gpt-5-2025-08-07
14.4%
#13Grok-4-0709
14.2%
#15gpt-4o-2024-08-06
14.1%
#16google/gemini-3.1-pro-preview
13.7%
#17openai/gpt-5.4-2026-03-05
13.5%
#18gpt-4.1-20250414
13.4%
#21claude-opus-4-5-20251101
13.1%
#22openai/gpt-4o-mini-2024-07-18
13.0%
#26gpt-5.1-2025-11-13
12.0%
#27claude-sonnet-4-20250514
11.9%
#29gemini-3-flash-preview
11.7%
#31google/gemini-3.1-flash-lite-preview
11.2%
#32xai-org/grok-4-fast-reasoning
11.0%
#34Qwen3-32B
10.8%
#35phi-4
10.7%
#36gemini-2.5-flash
10.7%
#39xai-org/grok-4-1-fast-reasoning
10.5%
#40anthropic/claude-opus-4-6-thinking
10.5%
#41gpt-5.2-2025-12-11
10.5%
#43kimi/kimi-k2.5-thinking
9.9%
#46anthropic/claude-opus-4-5-20251101-thinking
9.7%
#47google/gemini-2.0-flash-001
9.6%

Head-to-Head: #1 vs #2

#1

Top Pick

gemini-3-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct (88%) and FACTS Benchmark Suite facts_search_score_pct (100%)

19.9%

Conf 26.0%

#2

gpt-4o-20241120

Strong on DuckDB NSQL Leaderboard all_execution_accuracy (96%) and DuckDB NSQL Leaderboard hard_execution_accuracy (75%)

19.5%

Conf 36.6%

Full Comparison with Benchmark Evidence →
Full Use-Case PageBrowse All Use CasesHow We Score

Related Lookups

Best LLM for Code Generation

Benchmark-backed ranking of models for generating correct, secure code from requirements.

Best LLM for Debugging

Find the top-ranked models for localizing bugs and proposing fixes with explanations.

Best LLM for Unit Test Generation

Ranked models for generating meaningful unit tests and edge cases from code.

Best LLM for Code Review

Compare models for automated PR review covering correctness, security, and maintainability.

Best LLM for Refactoring

Ranked models for safely refactoring code while preserving behavior and improving clarity.

Best LLM for IDE Code Completion

Compare models for fast, accurate local-context code completion and snippet generation.