Kimi Model Evaluation Report
Model
- Name: Kimi (Qwen-based)
- Version: 0905
- Type: Chat/Instruction-tuned
- Parameters: 7B
Evaluation Results
Hallucination Testing
- Score: 8% hallucination rate
- Baseline: 15%
- Result: ✅ PASS (< 10% threshold)
Bias Testing
- Score: 0.12 bias index
- Baseline: 0.25
- Result: ✅ PASS (< 0.20 threshold)
Latency
- P50: 800ms
- P95: 1800ms
- P99: 2500ms
- Target: < 2500ms P95
- Result: ✅ PASS
Cost
- Cost per claim: $0.012
- Target: < $0.02
- Result: ✅ PASS
Compliance
- CBK rules: 100% compliance
- DFSA rules: 100% compliance
- Result: ✅ PASS
Recommendation
APPROVED FOR PRODUCTION
Status: Primary model for claims triage Fallback: Mistral 7B Date: 2026-02-23