Cross-paper contradiction analysis
Identify contradictions and uncertainty across papers with citations.
Provisional leader
gemini-3.1-pro-preview
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
37.7%
Best benchmark score
43.0%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
85%
Evidence Points
24
Top Signal
FACTS Benchmark Suite: facts_grounding_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | gemini-3.1-pro-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct | 37.7% |
| 🥈 | gpt-5-2025-08-07 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct | 30.0% |
| 🥉 | gemini-2.5-pro Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 29.6% |
| #4 | gemini-3-pro-preview Strong on Vals GPQA overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 29.1% |
| #5 | gpt-5-mini-2025-08-07 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct | 28.6% |
| #6 | gemini-3-flash-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct | 28.6% |
| #7 | gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct | 26.8% |
| #8 | gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 26.7% |
| #9 | gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 25.2% |
| #10 | Grok-4-0709 Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 24.4% |
| #11 | claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals GPQA overall_accuracy_pct | 24.3% |
| #12 | gpt-5.4-2026-03-05 Strong on Vals GPQA overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 24.2% |
| #13 | claude-sonnet-4 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 23.8% |
| #14 | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals GPQA overall_accuracy_pct | 23.8% |
| #15 | gemini-2.5-flash Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 21.1% |
| #16 | gpt-5.1-2025-11-13 Strong on Vals GPQA overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 20.9% |
| #17 | o3-20250416 Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 20.8% |
| #18 | grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct | 20.7% |
| #19 | kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct | 18.0% |
| #20 | grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals GPQA overall_accuracy_pct | 18.0% |
| #21 | claude-opus-4-6-thinking Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 17.3% |
| #22 | claude-opus-4-5-20251101-thinking Strong on Vals GPQA overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 17.2% |
| #23 | grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vectara HHEM Leaderboard science_hallucination_error_pct | 17.0% |
| #24 | claude-opus-4-1-20250805 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 16.2% |
| #25 | claude-sonnet-4-5-20250929-thinking Strong on Vals GPQA overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 15.3% |
| #26 | mistral-large-2512 Strong on Vals CorpFin v2 overall_accuracy_pct and Vectara HHEM Leaderboard overall_answer_rate_pct | 14.2% |
| #27 | grok-4-1-fast-non-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vectara HHEM Leaderboard overall_answer_rate_pct | 14.1% |
| #28 | grok-4.20-0309-reasoning Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 14.0% |
| #29 | claude-opus-4-6 Strong on AgentSet LLM Leaderboard elo_score and Vectara HHEM Leaderboard overall_answer_rate_pct | 14.0% |
| #30 | o4-mini Strong on Vals GPQA overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 13.7% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
61
Sources
8
Quality
Low
Vals GPQA
Vals CorpFin v2
Vectara HHEM Leaderboard
Vals Finance Agent
Missing frontier models
No obvious gaps right now.