BasedAGIBasedAGI
History

Historical document summarization

Summarize historical documents into timelines and key entities.

task.summarize_doctask.timeline_extraction
Evidence quality is currently limited for this use case. Rankings below are useful for exploration, not a strong winner claim.

Provisional leader

claude-sonnet-4

Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.

26.4%

Best benchmark score

35.4%

Confidence

Ranked Models

30

Evidence Quality

80%

Evidence Points

28

Top Signal

LanguageBench: overall:mean

All Ranked Models

30 of 30 models
RankModelScore
🥇claude-sonnet-4

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

26.4%
🥈gemini-2.5-flash

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

25.0%
#4gpt-4.1

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

20.6%
#5gemini-2.0-flash-001

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

20.2%
#7Claude-3.5-Sonnet

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

19.4%
#10gpt-5-2025-08-07

Strong on ExtractBench Paper Baselines credit_pass_rate_pct and Icelandic LLM Leaderboard Average ⬆️

15.4%
#12gpt-4.1-20250414

Strong on MMLongBench-Doc Leaderboard acc_score_pct and Galileo Agent Leaderboard v2 Avg AC

15.2%
#17Llama-3.3-70B-Instruct

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

14.3%
#19deepseek-r1

Strong on LanguageBench Translation Official (Split) translation_to:bleu and DuckDB NSQL Leaderboard all_execution_accuracy

12.9%
#20Llama-3.1-70B-Instruct

Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu

12.5%
#21gemini-3-pro-preview

Strong on Humanity's Last Exam Leaderboard hle_accuracy_pct and Icelandic LLM Leaderboard Average ⬆️

12.5%
#24gemini-3.1-pro-preview

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals MedCode overall_accuracy_pct

11.2%
#25gemini-2.5-pro

Strong on Galileo Agent Leaderboard v2 Avg AC and Galileo Agent Leaderboard v2 Avg TSQ

11.1%
#32gpt-5.2-2025-12-11

Strong on Humanity's Last Exam Leaderboard hle_accuracy_pct and BFCL Multi-turn Official Multi Turn Acc

9.8%
#33gpt-5-mini-2025-08-07

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals MedQA overall_accuracy_pct

9.8%
#34gpt-4o-20241120

Strong on MMLongBench-Doc Leaderboard acc_score_pct and DuckDB NSQL Leaderboard all_execution_accuracy

9.6%
#38Grok-4-0709

Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC

9.5%
#41gemini-3-flash-preview

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Legal Bench overall_accuracy_pct

9.4%
#45gpt-5.4-2026-03-05

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vectara HHEM Leaderboard overall_hallucination_error_pct

8.9%
#46phi-4

Strong on LanguageBench overall:mean and DuckDB NSQL Leaderboard all_execution_accuracy

8.7%
#47gpt-5.1-2025-11-13

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals MedScribe overall_accuracy_pct

8.6%
#48kimi-k2.5-thinking

Strong on Icelandic LLM Leaderboard Average ⬆️ and Humanity's Last Exam Leaderboard hle_accuracy_pct

8.6%
#49claude-sonnet-4.6

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Finance Agent overall_accuracy_pct

8.4%
#50claude-opus-4-5-20251101

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Mortgage Tax overall_accuracy_pct

8.3%
#52gemini-3.1-flash-lite-preview

Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Mortgage Tax overall_accuracy_pct

8.3%
#53o3-20250416

Strong on Aider Polyglot Leaderboard percent_correct_pct and Vals MedQA overall_accuracy_pct

8.1%
#54qwen-2.5-72b-instruct

Strong on DuckDB NSQL Leaderboard all_execution_accuracy and JSONSchemaBench Leaderboard medium_schema_compliance_pct

8.1%
#56gpt-4o

Strong on JSONSchemaBench Leaderboard medium_schema_compliance_pct and DuckDB NSQL Leaderboard all_execution_accuracy

7.7%
#57o4-mini

Strong on Icelandic LLM Leaderboard Average ⬆️ and Aider Polyglot Leaderboard percent_correct_pct

7.5%
#61gpt-4o-2024-08-06

Strong on DuckDB NSQL Leaderboard all_execution_accuracy and Icelandic LLM Leaderboard Average ⬆️

6.9%

Compare Models

Select two different models above to compare their evidence side by side.
Ranking diagnostics & missing models

Source lift

Ranked

37

Sources

8

Quality

Low

Vals Legal Bench

21 rows · 0.4% avg lift

Icelandic LLM Leaderboard

20 rows · 1.1% avg lift

Vals MedQA

20 rows · 0.4% avg lift

Vals Mortgage Tax

20 rows · 0.4% avg lift

Missing frontier models

grok-4-1-fast-non-reasoning

Thin evidence after weighting

Rank #15

14.9%

Taxonomy & task details

Core tasks

task.summarize_doctask.timeline_extraction

Required modes

mode.long_context

Domains

domain.history_linguistics

Related in History