Skip to content

Benchmark

MentalHealthBench · Acuity · Emergent

Scores are percentages. Higher is better.

Models and systems measured
16
Scores recorded
16
Sources
1
IQ weight
0.76

Score distribution

44.8%
Mean
46.1%
Median
10.2%
Std dev
31.8%
10th percentile
58%
90th percentile
24.1%
Min
24.1%58.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.76 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1GPT-6 AstraOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.3%
2GPT-6.1 SolGPT-6.1 Sol system card · max reasoning · four-response task mean · 344 tasks· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58%
3GPT-6 SolOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.1%
4Muse Spark 1.3OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs54.3%
5Claude Opus 5.5OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs53.9%
6GPT-6 LunaOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.6%
7Claude Fable 5.1OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs47.8%
8Claude Sonnet 5OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs43.1%
9Grok 4.7OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs41.5%
10Claude Haiku 4.5OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs41.1%
11Gemini 3.8 FlashOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs37.9%
12Gemini 3.1 Pro PreviewOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs31.8%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Gemini 2.5 ProOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs27.8%
GPT-4o (March 2025)OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.24.1%
GPT-5.6 Luna (Aug 2026)OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.43.7%
GPT-5.6 Sol (Aug 2026)OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.46.1%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.