BasedAGIBasedAGI

biomed_science

Best LLM for Literature Review

Ranked models for synthesizing papers and guidelines with citations and uncertainty.

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

google/gemini-3.1-pro-preview

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

external/google/gemini-3-1-pro-preview

30.2%

Score

35.0%

Confidence

23

Evidence

Ranked Models

30

Evidence Quality

83%

Evidence Points

23

Top Signal

FACTS Benchmark Suite: facts_grounding_score_pct

Benchmark Sources

36

Last Updated

8h ago

All Ranked Models

30 of 30 models
RankModelScore
🥇gemini-3.1-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct

30.2%
🥈gpt-5-2025-08-07

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct

25.8%
🥉gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

25.6%
#4gemini-3-flash-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct

25.2%
#5gpt-5-mini-2025-08-07

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct

24.7%
#6gemini-3-pro-preview

Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

24.3%
#7gpt-5.2-2025-12-11

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct

23.7%
#8gemini-3.1-flash-lite-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

23.1%
#9gpt-4.1-20250414

Strong on MMLongBench-Doc Leaderboard acc_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

21.8%
#10claude-opus-4.7

Strong on Vals Finance Agent overall_accuracy_pct and Vals GPQA overall_accuracy_pct

21.2%
#11claude-sonnet-4

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

21.0%
#12Grok-4-0709

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

20.8%
#13claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

20.7%
#14claude-opus-4-5-20251101

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct

20.6%
#15gpt-5.4-2026-03-05

Strong on Vals GPQA overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

20.2%
#16gemini-2.5-flash

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

18.6%
#18grok-4-fast-reasoning

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

17.6%
#19o3-20250416

Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

17.4%
#20gpt-5.1-2025-11-13

Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

17.2%
#21grok-4-1-fast-reasoning

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

16.9%
#24kimi-k2.5-thinking

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

15.4%
#25claude-opus-4-6-thinking

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

15.3%
#27phi-4

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

14.5%
#31grok-4-1-fast-non-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vectara HHEM Leaderboard overall_answer_rate_pct

13.7%
#32claude-opus-4-1-20250805

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

13.4%
#36o4-mini

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

12.4%
#37grok-4.20-0309-reasoning

Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

12.4%
#38qwen-2.5-72b-instruct

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

12.2%
#46Kimi K2 Thinking

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct

10.9%
#47claude-sonnet-4-5-20250929

Strong on Vals CorpFin v2 overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct

10.5%

Head-to-Head: #1 vs #2

#1

Top Pick

google/gemini-3.1-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct

30.2%

Conf 35.0%

#2

gpt-5-2025-08-07

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct

25.8%

Conf 35.0%

Related Lookups