Document summarization
Summarize long business documents into scannable outputs.
Provisional leader
gemini-2.5-pro
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
32.4%
Best benchmark score
50.1%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
83%
Evidence Points
34
Top Signal
FACTS Benchmark Suite: facts_grounding_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | gemini-2.5-pro Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 32.4% |
| 🥈 | gpt-5-2025-08-07 Strong on BasedAGI Document Summarization Eval overall_score_pct and FACTS Benchmark Suite facts_grounding_score_pct | 32.2% |
| 🥉 | gemini-3-pro-preview Strong on BasedAGI Document Summarization Eval overall_score_pct and SimpleQA Verified simpleqa_verified_score_pct | 32.2% |
| #4 | gemini-3.1-pro-preview Strong on SimpleQA Verified simpleqa_verified_score_pct and Vals Finance Agent overall_accuracy_pct | 31.3% |
| #5 | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and BasedAGI Document Summarization Eval overall_score_pct | 28.9% |
| #6 | Grok-4-0709 Strong on Vals Finance Agent overall_accuracy_pct and SimpleQA Verified simpleqa_verified_score_pct | 26.2% |
| #7 | gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 26.2% |
| #8 | gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 21.9% |
| #9 | gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Finance Agent overall_accuracy_pct | 21.9% |
| #10 | gemini-3-flash-preview Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_search_score_pct | 21.7% |
| #11 | gpt-4.1-20250414 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and MMLongBench-Doc Leaderboard acc_score_pct | 21.5% |
| #12 | gpt-5.4-2026-03-05 Strong on Vals Finance Agent overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 20.4% |
| #13 | claude-sonnet-4 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Galileo Agent Leaderboard v2 Avg TSQ | 19.9% |
| #14 | gemini-2.5-flash Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 19.0% |
| #15 | claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 18.7% |
| #16 | gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 18.0% |
| #17 | grok-4-fast-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 17.3% |
| #18 | o3-20250416 Strong on SciArena Leaderboard rating_elo and SimpleQA Verified simpleqa_verified_score_pct | 16.2% |
| #19 | grok-4-1-fast-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 14.7% |
| #20 | claude-opus-4-6-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 14.1% |
| #21 | kimi-k2.5-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 13.1% |
| #22 | claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 12.9% |
| #23 | grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and SimpleQA Verified simpleqa_verified_score_pct | 12.9% |
| #24 | claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 12.3% |
| #26 | claude-opus-4-1-20250805 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and FACTS Benchmark Suite facts_grounding_score_pct | 11.8% |
| #27 | grok-4.20-0309-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 11.6% |
| #28 | grok-4-1-fast-non-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 11.4% |
| #29 | mistral-large-2512 Strong on Vals CorpFin v2 overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 11.3% |
| #30 | glm-5-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 11.1% |
| #31 | claude-haiku-4-5-20251001-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct | 10.8% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
55
Sources
8
Quality
Low
Vals CorpFin v2
Vals Mortgage Tax
Vals Finance Agent
Vectara HHEM Leaderboard
Missing frontier models
No obvious gaps right now.
▶Taxonomy & task details
Core tasks
Required modes
Domains
Related in Productivity
Knowledge base Q&A (fast, no citations)
Answer KB questions grounded in retrieved text without citations.
Knowledge base Q&A (with citations)
Answer questions grounded in an internal KB, with evidence.
Decision memo
Recommend a decision with options, constraints, and risks.
Executive briefing
Turn raw notes into a short executive brief with risks and actions.