Health AI Benchmarks

SAFE-Teen (Vals AI)

Does the model respond safely when the stakes are personal?

More about this benchmark

How often chatbots fail a teen who hints at risk or turns down help; lower is better.

Whether chatbots stay safe when a teen (13 to 17) brings up a mental health concern: a simulated teen talks with each model for 6 to 20 turns, branching when the teen accepts or refuses help; a judge rates each conversation against a clinician rubric. Headline is the urgent-safety failure rate (suicide, self-harm, abuse, violence, eating disorders, psychosis, substance use) without a teen-aware system prompt.

On this site
17 of 18 models
Released
Oct 2026
Headline metric
Urgent safety failure rate, no teen-aware prompt
Official board updated
13 Oct 2026

Scores come from runs by the benchmark's maintainers or independent researchers.

Results
18 from 17 models
Latest
Oct 2026
Published by
Vals AI
Index weight
0.131, narrow, near its ceiling
Sources
1

Counts toward the Health Evals Index as a narrow benchmark, at weight 0.131: teen mental-health safety, one population. It is near its ceiling, with a leader at 85.0 out of 100, so it counts for less.

Where every published SAFE-Teen (Vals AI) score sits

18 scores, one column each, highest first, on the benchmark's own scale. Lower is better.

Each column is the model's lab colour. The table below says who ran each score.

Headline score

Every published score, ranked within this benchmark only

18 scores. Lower is better. Where the source gave a range, the whisker shows it. Open any row to read the sentence the score came from.

1GPT-6.1 SolOpenAI · no teen-aware prompt15Benchmark teamOct 2026[1]
GPT-6.1 Sol | 15% | 9% | 19% (Urgent safety | Health advice | Relationship boundaries)
In the source
15%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
2Claude Sonnet 5.5Anthropic · no teen-aware prompt23Benchmark teamOct 2026[1]
Claude Sonnet 5.5 | 23% | 43% | 37% (Urgent safety | Health advice | Relationship boundaries)
In the source
23%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
2GPT-5.6 LunaOpenAI · no teen-aware prompt23Benchmark teamOct 2026[1]
GPT-5.6 Luna | 23% | 21% | 35% (Urgent safety | Health advice | Relationship boundaries)
In the source
23%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
4Muse Spark 1.3 (Extra High)Meta · no teen-aware prompt26Benchmark teamOct 2026[1]
Muse Spark 1.3 (Extra High) | 26% | 14% | 56% (Urgent safety | Health advice | Relationship boundaries)
In the source
26%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt, Extra High
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
4Qwen 3.8 MaxAlibaba · no teen-aware prompt26Benchmark teamOct 2026[1]
Qwen 3.8 Max | 26% | 35% | 51% (Urgent safety | Health advice | Relationship boundaries)
In the source
26%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
6Claude Opus 5.5Anthropic · no teen-aware prompt27Benchmark teamOct 2026[1]
Claude Opus 5.5 | 27% | 44% | 25% (Urgent safety | Health advice | Relationship boundaries)
In the source
27%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
7DeepSeek V4.1 FlashDeepSeek · no teen-aware prompt31Benchmark teamOct 2026[1]
DeepSeek V4.1 Flash | 31% | 41% | 51% (Urgent safety | Health advice | Relationship boundaries)
In the source
31%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
8Mistral Large 4 PreviewMistral · no teen-aware prompt33Benchmark teamOct 2026[1]
Mistral Large 4 Preview | 33% | 53% | 19% (Urgent safety | Health advice | Relationship boundaries)
In the source
33%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
8Muse Spark 1.3 (Minimal)Meta · no teen-aware prompt33Benchmark teamOct 2026[1]
Muse Spark 1.3 (Minimal) | 33% | 29% | 70% (Urgent safety | Health advice | Relationship boundaries)
In the source
33%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt, Minimal
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
10MiMo v2.6 ProXiaomi · no teen-aware prompt40Benchmark teamOct 2026[1]
MiMo v2.6 Pro | 40% | 57% | 56% (Urgent safety | Health advice | Relationship boundaries)
In the source
40%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
11Grok 4.7SpaceX AI · no teen-aware prompt44Benchmark teamOct 2026[1]
Grok 4.7 | 44% | 39% | 48% (Urgent safety | Health advice | Relationship boundaries)
In the source
44%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
11Kimi K3Moonshot AI · no teen-aware prompt44Benchmark teamOct 2026[1]
Kimi K3 | 44% | 61% | 63% (Urgent safety | Health advice | Relationship boundaries)
In the source
44%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
13Grok 4.5SpaceX AI · no teen-aware prompt50Benchmark teamOct 2026[1]
Grok 4.5 | 50% | 47% | 65% (Urgent safety | Health advice | Relationship boundaries)
In the source
50%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
14GLM 5.3Zhipu · no teen-aware prompt51Benchmark teamOct 2026[1]
GLM 5.3 | 51% | 70% | 64% (Urgent safety | Health advice | Relationship boundaries)
In the source
51%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
15Gemini 3.6 FlashGoogle · no teen-aware prompt52Benchmark teamOct 2026[1]
Gemini 3.6 Flash | 52% | 68% | 70% (Urgent safety | Health advice | Relationship boundaries)
In the source
52%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
16Gemini 4 ArgonGoogle · no teen-aware prompt53Benchmark teamOct 2026[1]
Gemini 4 Argon | 53% | 71% | 66% (Urgent safety | Health advice | Relationship boundaries)
In the source
53%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
17MiniMax M3MiniMax · no teen-aware prompt54Benchmark teamOct 2026[1]
MiniMax M3 | 54% | 49% | 53% (Urgent safety | Health advice | Relationship boundaries)
In the source
54%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
18Gemini 3.8 FlashGoogle · no teen-aware prompt56Benchmark teamOct 2026[1]
Gemini 3.8 Flash | 56% | 69% | 63% (Urgent safety | Health advice | Relationship boundaries)
In the source
56%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
Health advice failure rate

Health advice failure rate, ranked on its own

18 scores. Lower is better. Where the source gave a range, the whisker shows it. Open any row to read the sentence the score came from.

1GPT-6.1 SolOpenAI · no teen-aware prompt9Benchmark teamOct 2026[1]
GPT-6.1 Sol | 15% | 9% | 19%
In the source
9%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
2Muse Spark 1.3 (Extra High)Meta · no teen-aware prompt14Benchmark teamOct 2026[1]
Muse Spark 1.3 (Extra High) | 26% | 14% | 56%
In the source
14%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt, Extra High
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
3GPT-5.6 LunaOpenAI · no teen-aware prompt21Benchmark teamOct 2026[1]
GPT-5.6 Luna | 23% | 21% | 35%
In the source
21%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
4Muse Spark 1.3 (Minimal)Meta · no teen-aware prompt29Benchmark teamOct 2026[1]
Muse Spark 1.3 (Minimal) | 33% | 29% | 70%
In the source
29%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt, Minimal
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
5Qwen 3.8 MaxAlibaba · no teen-aware prompt35Benchmark teamOct 2026[1]
Qwen 3.8 Max | 26% | 35% | 51%
In the source
35%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
6Grok 4.7SpaceX AI · no teen-aware prompt39Benchmark teamOct 2026[1]
Grok 4.7 | 44% | 39% | 48%
In the source
39%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
7DeepSeek V4.1 FlashDeepSeek · no teen-aware prompt41Benchmark teamOct 2026[1]
DeepSeek V4.1 Flash | 31% | 41% | 51%
In the source
41%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
8Claude Sonnet 5.5Anthropic · no teen-aware prompt43Benchmark teamOct 2026[1]
Claude Sonnet 5.5 | 23% | 43% | 37%
In the source
43%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
9Claude Opus 5.5Anthropic · no teen-aware prompt44Benchmark teamOct 2026[1]
Claude Opus 5.5 | 27% | 44% | 25%
In the source
44%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
10Grok 4.5SpaceX AI · no teen-aware prompt47Benchmark teamOct 2026[1]
Grok 4.5 | 50% | 47% | 65%
In the source
47%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
11MiniMax M3MiniMax · no teen-aware prompt49Benchmark teamOct 2026[1]
MiniMax M3 | 54% | 49% | 53%
In the source
49%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
12Mistral Large 4 PreviewMistral · no teen-aware prompt53Benchmark teamOct 2026[1]
Mistral Large 4 Preview | 33% | 53% | 19%
In the source
53%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
13MiMo v2.6 ProXiaomi · no teen-aware prompt57Benchmark teamOct 2026[1]
MiMo v2.6 Pro | 40% | 57% | 56%
In the source
57%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
14Kimi K3Moonshot AI · no teen-aware prompt61Benchmark teamOct 2026[1]
Kimi K3 | 44% | 61% | 63%
In the source
61%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
15Gemini 3.6 FlashGoogle · no teen-aware prompt68Benchmark teamOct 2026[1]
Gemini 3.6 Flash | 52% | 68% | 70%
In the source
68%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
16Gemini 3.8 FlashGoogle · no teen-aware prompt69Benchmark teamOct 2026[1]
Gemini 3.8 Flash | 56% | 69% | 63%
In the source
69%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
17GLM 5.3Zhipu · no teen-aware prompt70Benchmark teamOct 2026[1]
GLM 5.3 | 51% | 70% | 64%
In the source
70%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
18Gemini 4 ArgonGoogle · no teen-aware prompt71Benchmark teamOct 2026[1]
Gemini 4 Argon | 53% | 71% | 66%
In the source
71%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
Relationship boundaries failure rate

Relationship boundaries failure rate, ranked on its own

18 scores. Lower is better. Where the source gave a range, the whisker shows it. Open any row to read the sentence the score came from.

1GPT-6.1 SolOpenAI · no teen-aware prompt19Benchmark teamOct 2026[1]
GPT-6.1 Sol | 15% | 9% | 19%
In the source
19%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
1Mistral Large 4 PreviewMistral · no teen-aware prompt19Benchmark teamOct 2026[1]
Mistral Large 4 Preview | 33% | 53% | 19%
In the source
19%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
3Claude Opus 5.5Anthropic · no teen-aware prompt25Benchmark teamOct 2026[1]
Claude Opus 5.5 | 27% | 44% | 25%
In the source
25%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
4GPT-5.6 LunaOpenAI · no teen-aware prompt35Benchmark teamOct 2026[1]
GPT-5.6 Luna | 23% | 21% | 35%
In the source
35%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
5Claude Sonnet 5.5Anthropic · no teen-aware prompt37Benchmark teamOct 2026[1]
Claude Sonnet 5.5 | 23% | 43% | 37%
In the source
37%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
6Grok 4.7SpaceX AI · no teen-aware prompt48Benchmark teamOct 2026[1]
Grok 4.7 | 44% | 39% | 48%
In the source
48%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
7DeepSeek V4.1 FlashDeepSeek · no teen-aware prompt51Benchmark teamOct 2026[1]
DeepSeek V4.1 Flash | 31% | 41% | 51%
In the source
51%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
7Qwen 3.8 MaxAlibaba · no teen-aware prompt51Benchmark teamOct 2026[1]
Qwen 3.8 Max | 26% | 35% | 51%
In the source
51%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
9MiniMax M3MiniMax · no teen-aware prompt53Benchmark teamOct 2026[1]
MiniMax M3 | 54% | 49% | 53%
In the source
53%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
10MiMo v2.6 ProXiaomi · no teen-aware prompt56Benchmark teamOct 2026[1]
MiMo v2.6 Pro | 40% | 57% | 56%
In the source
56%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
10Muse Spark 1.3 (Extra High)Meta · no teen-aware prompt56Benchmark teamOct 2026[1]
Muse Spark 1.3 (Extra High) | 26% | 14% | 56%
In the source
56%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt, Extra High
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
12Gemini 3.8 FlashGoogle · no teen-aware prompt63Benchmark teamOct 2026[1]
Gemini 3.8 Flash | 56% | 69% | 63%
In the source
63%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
12Kimi K3Moonshot AI · no teen-aware prompt63Benchmark teamOct 2026[1]
Kimi K3 | 44% | 61% | 63%
In the source
63%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
14GLM 5.3Zhipu · no teen-aware prompt64Benchmark teamOct 2026[1]
GLM 5.3 | 51% | 70% | 64%
In the source
64%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
15Grok 4.5SpaceX AI · no teen-aware prompt65Benchmark teamOct 2026[1]
Grok 4.5 | 50% | 47% | 65%
In the source
65%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
16Gemini 4 ArgonGoogle · no teen-aware prompt66Benchmark teamOct 2026[1]
Gemini 4 Argon | 53% | 71% | 66%
In the source
66%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
17Gemini 3.6 FlashGoogle · no teen-aware prompt70Benchmark teamOct 2026[1]
Gemini 3.6 Flash | 52% | 68% | 70%
In the source
70%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
17Muse Spark 1.3 (Minimal)Meta · no teen-aware prompt70Benchmark teamOct 2026[1]
Muse Spark 1.3 (Minimal) | 33% | 29% | 70%
In the source
70%
Where to find it
vals.ai/benchmarks/mental-health, results table (No teen-aware prompt)
How it was run
no teen-aware prompt, Minimal
Reported by
official leaderboard
Document
[1] SAFE-Teen, Vals AI
Sources

The 1 document behind these scores

  1. 1.SAFE-Teen, Vals AIofficial leaderboard, Vals AI, 13 Oct 2026. Quotes from this document