List your company

Legal Domain Fabrication and Factuality Analysis on JURIDICO-FCR 75 tasks

0.11Average FCRGPT-5.2 (gpt-5.2-2025-12-11)
-1.48569.284720.05530.8253Jan 21, 2026

Evaluation results

MethodLinks
GPT-5.2 (gpt-5.2-2025-12-11)Paradigm=Advanced RAG2026.010.110.11.10.5
Gemini 3.0 Pro (gemini-3.0-pro)Paradigm=Advanced RAG2026.010.120.111.40.6
GPT-4.1 (gpt-4.1-2025-04-14)Paradigm=Advanced RAG2026.010.130.111.60.8
DeepSeek V3.1 Terminus (deepseek-v3.1-terminus)Paradigm=Advanced RAG2026.010.130.121.71
Kimi K2 Thinking (Kimi-K2-Thinking)Paradigm=Advanced RAG2026.010.140.1221.1
Claude 4.5 Sonnet (claude-sonnet-4-5...)Paradigm=Advanced RAG2026.010.140.132.41.2
Qwen3 235B A22B Instruct (Qwen3-235B-A22B...)Paradigm=Advanced RAG2026.010.150.132.21.3
Gemma 3 27B (gemma-3-27b-it)Paradigm=Advanced RAG2026.010.150.142.61.4
Llama 4 Maverick (Llama-4-Maverick...)Paradigm=Advanced RAG2026.010.160.142.71.5
Mistral Small 24B (Mistral-Small-24B...)Paradigm=Advanced RAG2026.010.170.153.11.7
Gemini Flash Latest (gemini-flash-preview...)Paradigm=Advanced RAG2026.010.180.153.31.8
Claude 4.1 Opus (claude-opus-4-1...)Paradigm=Advanced RAG2026.010.190.163.51.9
GPT-5.2 (gpt-5.2-2025-12-11)Paradigm=Canonical RAG2026.014.23.1106.2
Gemini 3.0 Pro (gemini-3.0-pro)Paradigm=Canonical RAG2026.014.93.311.57
GPT-4.1 (gpt-4.1-2025-04-14)Paradigm=Canonical RAG2026.015.34.8138.5
Kimi K2 Thinking (Kimi-K2-Thinking)Paradigm=Canonical RAG2026.016.85.915.510.5
DeepSeek V3.1 Terminus (deepseek-v3.1-terminus)Paradigm=Canonical RAG2026.017.15.2149
Claude 4.5 Sonnet (claude-sonnet-4-5...)Paradigm=Canonical RAG2026.018.16.21511.5
Qwen3 235B A22B Instruct (Qwen3-235B-A22B...)Paradigm=Canonical RAG2026.018.96.51611
Llama 4 Maverick (Llama-4-Maverick...)Paradigm=Canonical RAG2026.019.57.81813.5
Gemma 3 27B (gemma-3-27b-it)Paradigm=Canonical RAG2026.0110.87.21712.5
Mistral Small 24B (Mistral-Small-24B...)Paradigm=Canonical RAG2026.01128.51914
Gemini Flash Latest (gemini-flash-preview...)Paradigm=Canonical RAG2026.0113.29.120.515.5
Claude 4.1 Opus (claude-opus-4-1...)Paradigm=Canonical RAG2026.0114.89.82116.5
GPT-5.2 (gpt-5.2-2025-12-11)Paradigm=Direct2026.0115.18.235.523
Gemini 3.0 Pro (gemini-3.0-pro)Paradigm=Direct2026.0116.88.53825.5
GPT-4.1 (gpt-4.1-2025-04-14)Paradigm=Direct2026.0118.510.94327
Kimi K2 Thinking (Kimi-K2-Thinking)Paradigm=Direct2026.0121.913.25036
DeepSeek V3.1 Terminus (deepseek-v3.1-terminus)Paradigm=Direct2026.0122.411.54832
Qwen3 235B A22B Instruct (Qwen3-235B-A22B...)Paradigm=Direct2026.0126.514.85337
Claude 4.5 Sonnet (claude-sonnet-4-5...)Paradigm=Direct2026.0128.215.55941
Gemma 3 27B (gemma-3-27b-it)Paradigm=Direct2026.0130.218.15942
Llama 4 Maverick (Llama-4-Maverick...)Paradigm=Direct2026.013116.96244
Mistral Small 24B (Mistral-Small-24B...)Paradigm=Direct2026.0134.519.26447
Gemini Flash Latest (gemini-flash-preview...)Paradigm=Direct2026.0136.820.96750
Claude 4.1 Opus (claude-opus-4-1...)Paradigm=Direct2026.014021.86952.5