BasedAGIBasedAGI

business_productivity

Best Model for RAG Q&A With Citations

Find the best model for grounded Q&A with citations from internal knowledge bases.

Full Analysis Available

Benchmark methodology, patterns in the data, and deployment notes

This page is high-intent, but the current benchmark evidence for this use case is still limited. Treat the leader below as provisional.

Provisional leader

gemini-2.5-pro

Best current option from the available benchmark evidence, but not yet a strong winner claim.

external/google/gemini-2-5-pro

31.6%

Score

48.1%

Confidence

34

Evidence

$3.44

per 1M tokens

Ranked Models

30

Evidence Quality

83%

Evidence Points

34

Top Signal

FACTS Benchmark Suite: facts_grounding_score_pct

Benchmark Sources

35

Last Updated

16h ago

All Ranked Models

30 of 30 models
RankModelScore
🥇gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct and BasedAGI KB Q&A Eval overall_score_pct

31.6%
🥈gpt-5-2025-08-07

Strong on BasedAGI KB Q&A Eval overall_score_pct and FACTS Benchmark Suite facts_grounding_score_pct

30.4%
🥉gemini-3-pro-preview

Strong on BasedAGI KB Q&A Eval overall_score_pct and Vals Finance Agent overall_accuracy_pct

27.0%
#4gemini-3.1-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_search_score_pct

26.7%
#5claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

26.2%
#6gpt-5-mini-2025-08-07

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

25.6%
#7Grok-4-0709

Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct

23.9%
#8gemini-3-flash-preview

Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite average_score_pct

22.3%
#9gemini-3.1-flash-lite-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

21.0%
#10gpt-5.2-2025-12-11

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Finance Agent overall_accuracy_pct

20.8%
#11claude-sonnet-4

Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Galileo Agent Leaderboard v2 Avg TSQ

19.4%
#12gpt-4.1-20250414

Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct

18.7%
#13gpt-5.4-2026-03-05

Strong on Vals Finance Agent overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

18.4%
#14gemini-2.5-flash

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

17.8%
#16claude-opus-4-5-20251101

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

16.6%
#17grok-4-fast-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

16.1%
#19gpt-5.1-2025-11-13

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

15.9%
#20grok-4-1-fast-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

14.4%
#21o3-20250416

Strong on SciArena Leaderboard rating_elo and FACTS Benchmark Suite facts_search_score_pct

13.8%
#23claude-opus-4-6-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

13.8%
#24claude-opus-4.7

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

13.8%
#25qwen-2.5-72b-instruct

Strong on Open LLM Leaderboard MMLU-Pro mmlu_pro_accuracy_pct and Open LLM Leaderboard GPQA gpqa

13.8%
#27kimi-k2.5-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

13.3%
#28phi-4

Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Open LLM Leaderboard GPQA gpqa

12.9%
#33grok-4-1-fast-non-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

11.6%
#34grok-4.20-0309-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct

11.4%
#42claude-opus-4-1-20250805

Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and FACTS Benchmark Suite facts_grounding_score_pct

10.2%
#46gpt-4o-2024-08-06

Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vectara HHEM Leaderboard overall_answer_rate_pct

9.4%
#48gemini-2.5-flash-lite

Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Galileo Agent Leaderboard v2 Avg TSQ

9.4%
#49o4-mini

Strong on Vals CorpFin v2 overall_accuracy_pct and SciArena Leaderboard rating_elo

9.3%

Head-to-Head: #1 vs #2

#1

Top Pick

gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct and BasedAGI KB Q&A Eval overall_score_pct

31.6%

Conf 48.1%

#2

gpt-5-2025-08-07

Strong on BasedAGI KB Q&A Eval overall_score_pct and FACTS Benchmark Suite facts_grounding_score_pct

30.4%

Conf 40.1%

Related Lookups