MindEval2 MHQR GPT-6.1 Sol High: leaderboard
MindEval2 MHQR clinical response quality: weighted issue severity0/1/5/10, lower is better; 50 patients over3 sessions, 150 patient-session scores, 61819 replies. Counsellors temperature1 and provider defaults; DeepSeek V4.1 Flash thinking patient simulator. GPT-6.1 Sol High judge; same replies across judge variants. Shared-family self-preference and clinician disagreement are limitations; not a clinical-effectiveness claim. Metric: MHQR (0–10, lower better). Lower is better. Source: https://arxiv.org/html/2610.22314v1
Metric: MHQR (0–10, lower better). Source: arxiv.org. Saturation forecast: Around January 2027. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Terra | 0.84 | #39 |
| 2 | GPT-5.6 Sol | 0.91 | #18 |
| 3 | GPT-5.6 Luna | 1.13 | #68 |
| 4 | Claude Sonnet 5 | 2.22 | #54 |
| 5 | Kimi K3 | 2.51 | #29 |
| 6 | GLM-5.3 | 2.53 | #40 |
| 7 | Claude Opus 5 | 2.6 | #12 |
| 8 | Qwen 3.8 27B | 2.97 | #98 |
| 9 | Gemini 3.8 Flash | 3.08 | #21 |
| 10 | Qwen 3.5 397B A17B | 3.52 | #145 |
| 11 | Qwen 3.5 27B | 3.9 | #185 |
| 12 | Qwen 3.5 122B A10B | 4.12 | #171 |
| 13 | Gemma 4 31B | 4.12 | #197 |
| 14 | Gemma 4 26B A4B | 4.16 | #350 |
| 15 | Muse Glimmer 30B | 4.31 | #178 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=mindeval2-mhqr-gpt-6-1-sol-high · How It Works · Data refreshed daily, snapshot 2026-10-17.