Skip to content

Benchmark

DAYJOB: Healthcare

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
15
Scores recorded
15
Sources
1
IQ weight
0.97

Score distribution

22.8%
Mean
23.6%
Median
11.2%
Std dev
7.2%
10th percentile
34%
90th percentile
6.4%
Min
6.4%48.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.97 for chat models, measured over 15 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Opus 5.5clinical-result-2586· Clinical Benchmarks data docs48.3%
2Claude Sonnet 5.5clinical-result-2587· Clinical Benchmarks data docs34%
3Claude Fable 5.1clinical-result-2589· Clinical Benchmarks data docs31.2%
4Muse Wonderclinical-result-2588· Clinical Benchmarks data docs31.2%
5GPT-6 Astraclinical-result-2590· Clinical Benchmarks data docs28.4%
6Grok 4.7clinical-result-2591· Clinical Benchmarks data docs27.6%
7GPT-6.1 Solclinical-result-2592· Clinical Benchmarks data docs25.2%
8Gemini 4 Argonclinical-result-2593· Clinical Benchmarks data docs23.6%
9Claude Opus 5clinical-result-2594· Clinical Benchmarks data docs22%
10Muse Spark 1.3clinical-result-2595· Clinical Benchmarks data docs22%
11Grok 4.6clinical-result-2596· Clinical Benchmarks data docs14.8%
12Claude Fable 5clinical-result-2597· Clinical Benchmarks data docs11.2%
13Muse Spark 1.2clinical-result-2598· Clinical Benchmarks data docs8.8%
14GPT-6 Solclinical-result-2599· Clinical Benchmarks data docs7.2%
15Hy4 previewclinical-result-2600· Clinical Benchmarks data docs6.4%

Data credits: Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)