Fraud signal summary
Summarize potential fraud indicators with conservative evidence framing.
Provisional leader
gemini-2.5-pro
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
26.5%
Best benchmark score
41.3%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
81%
Evidence Points
32
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 | 26.5% |
| 🥈 | gpt-4.1-20250414 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Galileo Agent Leaderboard v2 Insurance AC | 25.6% |
| 🥉 | gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_search_score_pct | 24.8% |
| #4 | gpt-5-2025-08-07 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Finance Agent overall_accuracy_pct | 22.3% |
| #5 | claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Insurance TSQ and Vectara HHEM Leaderboard overall_hallucination_error_pct | 22.1% |
| #6 | Grok-4-0709 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 22.0% |
| #7 | gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 21.4% |
| #8 | gemini-2.5-flash Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 19.7% |
| #9 | gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct | 19.0% |
| #10 | gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 18.9% |
| #11 | gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct | 18.3% |
| #12 | gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 17.4% |
| #13 | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 17.3% |
| #14 | gpt-5.4-2026-03-05 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct | 16.3% |
| #15 | claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct | 15.8% |
| #16 | gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 14.7% |
| #17 | grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 14.6% |
| #18 | gpt-4.1-mini-20250414 Strong on OpenVLM OCRBench Official ocrbench_score_pct and Vals CorpFin v2 overall_accuracy_pct | 14.5% |
| #19 | o3-20250416 Strong on Vals CorpFin v2 overall_accuracy_pct and SciArena Leaderboard rating_elo | 14.4% |
| #20 | grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 13.1% |
| #21 | claude-opus-4-6-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 12.1% |
| #22 | kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 11.5% |
| #23 | grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct | 11.3% |
| #24 | claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 11.2% |
| #25 | qwen-2.5-72b-instruct Strong on Galileo Agent Leaderboard v2 Insurance AC and DuckDB NSQL Leaderboard all_execution_accuracy | 11.2% |
| #26 | Claude-3.5-Sonnet Strong on LLM-AggreFact Leaderboard average_score_pct and OpenVLM OCRBench Official ocrbench_score_pct | 11.0% |
| #27 | claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 10.5% |
| #28 | deepseek-v3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vectara HHEM Leaderboard overall_answer_rate_pct | 10.3% |
| #30 | grok-4.20-0309-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 10.2% |
| #31 | glm-5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 10.2% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
57
Sources
8
Quality
Low
Vals CorpFin v2
Vals MedQA
Vals Legal Bench
Vals Tax Eval v2
Missing frontier models
No obvious gaps right now.
▶Taxonomy & task details
Core tasks
Required modes
Domains
Related in Insurance
Litigation risk memo
Summarize a claim into litigation risk drivers and mitigation steps.
Policy wording comparison
Compare policy wording against a standard and flag material differences.
Claims summary
Summarize claim history into timeline, status, and open items.
Underwriting submission ingest
Convert messy submission docs into structured underwriting fields.