BasedAGIBasedAGI
Finance

Filings summarization (10-K/10-Q)

Summarize filings with conservative factuality and risk highlights.

task.summarize_doctask.entity_extraction

Best for this use case

gemini-3.1-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

38.5%

Best benchmark score

44.2%

Confidence

Ranked Models

30

Evidence Quality

87%

Evidence Points

28

Top Signal

Vals Finance Agent: overall_accuracy_pct

All Ranked Models

30 of 30 models
RankModelScore
๐Ÿฅ‡gemini-3.1-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

38.5%
๐ŸฅˆGrok-4-0709

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

32.6%
๐Ÿฅ‰gpt-5-2025-08-07

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

32.4%
#4gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct

31.9%
#5gpt-5-mini-2025-08-07

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

31.3%
#6gpt-5.2-2025-12-11

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

31.2%
#7claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

30.5%
#8gemini-3-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

30.5%
#9gemini-3-flash-preview

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

29.5%
#10gpt-4.1-20250414

Strong on Vals CorpFin v2 overall_accuracy_pct and MMLongBench-Doc Leaderboard acc_score_pct

29.2%
#11gpt-5.4-2026-03-05

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

29.0%
#12gemini-3.1-flash-lite-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

28.4%
#13grok-4-fast-reasoning

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

26.2%
#14gpt-5.1-2025-11-13

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

26.1%
#15grok-4-1-fast-reasoning

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

24.2%
#16claude-sonnet-4

Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct

24.1%
#17claude-opus-4-6-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

24.0%
#18claude-opus-4-5-20251101-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

22.9%
#19claude-opus-4-5-20251101

Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct

22.8%
#20kimi-k2.5-thinking

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

22.5%
#21claude-sonnet-4-5-20250929-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

21.3%
#22grok-4.20-0309-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

21.0%
#24o3-20250416

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct

19.9%
#25glm-5-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

19.6%
#26qwen3.5-flash

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

19.5%
#28claude-haiku-4-5-20251001-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

18.9%
#29gpt-5.4-nano-2026-03-17

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

18.8%
#30MiniMax-M2.7

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

18.2%
#31grok-4-1-fast-non-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

17.2%
#32mistral-large-2512

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct

16.7%

Compare Models

Select two different models above to compare their evidence side by side.
โ–ถRanking diagnostics & missing models

Source lift

Ranked

54

Sources

8

Quality

Good

Vals Tax Eval v2

45 rows ยท 1.4% avg lift

Vals CorpFin v2

44 rows ยท 1.5% avg lift

Vals GPQA

36 rows ยท 0.6% avg lift

Vals Mortgage Tax

33 rows ยท 1.1% avg lift

Missing frontier models

No obvious gaps right now.

โ–ถTaxonomy & task details

Core tasks

task.summarize_doctask.entity_extraction

Required modes

mode.long_context

Domains

domain.finance_equity_research

Related in Finance