BasedAGIBasedAGI
Menu
Rankings live

business_productivity

Document summarization

Summarize long business documents into scannable outputs.

#1 Recommendation

gemini-3-pro-preview

Strong on BasedAGI Document Summarization Eval overall_score_pct (100%) and FACTS Benchmark Suite facts_grounding_score_pct (88%)

external/google/gemini-3-pro-preview

39.1%

Score

49.6%

Confidence

Limited benchmark evidence for this use case.

49 ranked models with average evidence of 16.1 points. Rankings may shift as more benchmark data is ingested.

Ranked Models

30

Evidence Quality

83%

Scoring

Benchmark-backed

Top Signal

BasedAGI Document Summarization Eval: overall_score_pct

All Ranked Models

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

Strong on BasedAGI Document Summarization Eval overall_score_pct (100%) and FACTS Benchmark Suite facts_grounding_score_pct (88%)

39.1%
#2gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct (100%) and Vectara HHEM Leaderboard overall_hallucination_error_pct (76%)

33.8%
#3anthropic/claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct (100%) and BasedAGI Document Summarization Eval overall_score_pct (80%)

30.5%
#4Grok-4-0709
24.6%
#5gpt-4.1-20250414
22.7%
#6gpt-5-mini-2025-08-07
22.5%
#7gpt-5-2025-08-07
21.3%
#8google/gemini-3.1-pro-preview
20.4%
#9openai/gpt-5.4-2026-03-05
20.3%
#10gemini-2.5-flash
18.5%
#11claude-opus-4-5-20251101
18.3%
#12claude-sonnet-4-20250514
17.6%
#13gpt-5.1-2025-11-13
17.5%
#14google/gemini-3.1-flash-lite-preview
17.2%
#15gemini-3-flash-preview
15.6%
#16xai-org/grok-4-fast-reasoning
15.6%
#17gpt-5.2-2025-12-11
15.3%
#18anthropic/claude-opus-4-6-thinking
14.9%
#19xai-org/grok-4-1-fast-reasoning
14.7%
#20kimi/kimi-k2.5-thinking
13.8%
#21anthropic/claude-opus-4-5-20251101-thinking
13.7%
#22anthropic/claude-sonnet-4-5-20250929-thinking
13.0%
#25mistralai/mistral-large-2512
12.0%
#26x-ai/grok-3
11.8%
#27zai/glm-5-thinking
11.7%
#28anthropic/claude-haiku-4-5-20251001-thinking
11.5%
#29xai-org/grok-4-1-fast-non-reasoning
11.4%
#30alibaba/qwen3.5-flash
11.3%
#31anthropic/claude-opus-4-1-20250805
11.2%
#32o3-20250416
10.6%

Compare Models

Model A leads by +5.3%

Shareable Link →

Model A

gemini-3-pro-preview

external/google/gemini-3-pro-preview

39.1%

Rank #1

Confidence 49.6%29 evidence pts

BasedAGI Document Summarization Eval: overall_score_pct

Value 100.0% · Conf 100.0% · Weight 3.7%

basedagi_doc_summarization_eval.overall_score_pct (Mar 12, 2026)

FACTS Benchmark Suite: facts_grounding_score_pct

Value 88.3% · Conf 100.0% · Weight 3.0%

facts_benchmark_suite.facts_grounding_score_pct (Mar 12, 2026)

Vals Finance Agent: overall_accuracy_pct

Value 87.0% · Conf 100.0% · Weight 2.8%

vals_finance_agent.overall_accuracy_pct (Mar 12, 2026)

FACTS Benchmark Suite: facts_search_score_pct

Value 100.0% · Conf 100.0% · Weight 2.6%

facts_benchmark_suite.facts_search_score_pct (Mar 12, 2026)

Model B

gemini-2.5-pro

external/google/gemini-2-5-pro

33.8%

Rank #2

Confidence 51.5%30 evidence pts

FACTS Benchmark Suite: facts_grounding_score_pct

Value 100.0% · Conf 100.0% · Weight 3.4%

facts_benchmark_suite.facts_grounding_score_pct (Mar 12, 2026)

Vectara HHEM Leaderboard: overall_hallucination_error_pct

Value 76.0% · Conf 100.0% · Weight 2.7%

vectara_hhem_leaderboard.overall_hallucination_error_pct (Mar 12, 2026)

BasedAGI Document Summarization Eval: overall_score_pct

Value 66.7% · Conf 100.0% · Weight 2.5%

basedagi_doc_summarization_eval.overall_score_pct (Mar 12, 2026)

Vals Finance Agent: overall_accuracy_pct

Value 65.5% · Conf 100.0% · Weight 2.1%

vals_finance_agent.overall_accuracy_pct (Mar 12, 2026)

Ranking Diagnostics & Missing Models

Source Lift

Ranked

49

Sources

8

Quality

Insufficient

Vals CorpFin v2

vals_corp_fin_v2

42 rows

1.1% avg lift

Vals Mortgage Tax

vals_mortgage_tax

32 rows

1.0% avg lift

Vals Legal Bench

vals_legal_bench

32 rows

0.3% avg lift

Vals MedQA

vals_medqa

30 rows

0.3% avg lift

Missing Strong Models

gpt-4o

external/openai/gpt-4o

Rank #22

15.2%

Thin evidence after weighting
Taxonomy Details

Core Tasks

task.summarize_doc

Required Modes

mode.long_context

Domains

domain.general_business

Related Use Cases