Skip to content

Benchmark

HealthBench Professional

Scores are percentages. Higher is better.

Models and systems measured
45
Scores recorded
113
Sources
3
IQ weight
2.33

Score distribution

58.2%
Mean
59.8%
Median
8.5%
Std dev
46.2%
10th percentile
66.3%
90th percentile
32.2%
Min
32.2%77.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.33 for chat models, measured over 43 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
51GPT-5.6 SolOpus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.5%
52Muse Wonder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
53Muse Wonderclinical-result-2405· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
54Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
55Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.8%
56Claude Opus 5clinical-result-206· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim59.8%
57Claude Opus 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.8%
58Claude Opus 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · length-adjusted · same Opus 5.5 card setup· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.8%
59Claude Opus 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.8%
60Muse Spark 1.1clinical-result-505· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim59.3%
61Muse Spark 1.1Meta Model API · xhigh · 525 items · length-normalized · GPT-5.4 low grader· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.3%
62Claude Fable 5.1length-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.1%
63Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.8%
64Claude Sonnet 5clinical-result-207· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim57.8%
65Claude Sonnet 5length-adjusted · Opus 4.8 grader · no tools · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.8%
66GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.7%
67GPT-5.6 Terraclinical-result-208· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim57.7%
68GPT-5.6 TerraOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.7%
69Claude Opus 4.8clinical-result-1871· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim57.4%
70Claude Opus 4.8Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.4%
71Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.9%
72Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.7%
73Grok 4.7clinical-result-1804· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim56.7%
74Grok 4.7length-adjusted score · rejected requests scored zero · xhigh effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.7%
75Claude Opus 5length-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.4%
76Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.8%
77Claude Opus 4.8clinical-result-209· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim55.8%
78Claude Opus 4.8max · 525 items · length-normalized · GPT-5.4 low grader· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.8%
79GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.7%
80GPT-5.6 Lunaclinical-result-210· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim55.7%
81GPT-5.6 LunaOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.7%
82Gemini 4 Argonclinical-result-2385· Clinical Benchmarks data docs55.1%
83Ling 3.0 Flash SanteLing-3.0-flash-Sante official evaluation image · highest reasoning tier · temperature 1.0 / top_p 0.95 unless otherwise stated · exact API snapshot and run count not published · professional healthcare score· Reported by Ant inclusionAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.3%
84Muse Sparkclinical-result-506· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim54.1%
85GPT-5.6 Solclinical-result-492· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim54%
86Kimi K3clinical-result-2386· Clinical Benchmarks data docs53.2%
87Claude Opus 4.8OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53%
88GLM 5.3clinical-result-2387· Clinical Benchmarks data docs52.8%
89Gemini 3.8 Flashlength-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.1%
90Claude Opus 4.7clinical-result-504· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim51.9%
91GPT 5.5clinical-result-489· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim51.8%
92GPT 5.5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.51.8%
93GPT 5.5length-adjusted · no tools · GPT-5.5 system-card implementation· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.51.8%
94GPT 5.5xhigh · 525 items · length-normalized · GPT-5.4 low grader· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.51.8%
95Gemini 3.8 Flashclinical-result-2388· Clinical Benchmarks data docs51.7%
96DeepSeek V4.1 Flashclinical-result-2389· Clinical Benchmarks data docs50.7%
97GPT 5.5OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.5%
98Grok 4.6clinical-result-1805· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim48.5%
99GPT 5.4clinical-result-488· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim48.1%
100GPT 5clinical-result-485· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim46.2%

Showing 51–100 of 111 results.

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
Grok 4.6length-adjusted score · rejected requests scored zero · xhigh effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.48.5%
Muse Spark (version unspecified)Meta Model API · highest effort · version unspecified · 525 items · length-normalized · GPT-5.4 low grader· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.1%

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