BDR-AI's picture
Initial commit for claims-gpt-model-registry
9fe93c4 verified
|
Raw History Blame Contribute Delete
567 Bytes

Mistral Model Evaluation Report

Model

  • Name: Mistral 7B
  • Version: Instruct v0.1
  • Type: Chat
  • Parameters: 7B

Evaluation Results

Hallucination Testing

  • Score: 18% hallucination rate
  • Result: ⚠️ CONDITIONAL PASS

Latency

  • P95: 3200ms
  • Result: ⚠️ EXCEEDS TARGET

Cost

  • Cost per claim: $0.008
  • Result: ✅ BEST COST

Recommendation

APPROVED FOR COST CONTAINMENT ONLY

Use when: Cost budget near limit + low complexity claims Primary: Kimi 0905 Fallback: Mixtral 8x7B Date: 2026-02-23