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
1Claude Opus 5.5Opus 5.5 System Card · adaptive thinking · max effort unless stated · raw · no tools · Opus 4.8 grader · max · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.1%
2Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · raw · no tools · Opus 4.8 grader · max · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.1%
3Claude Fable 5.1Opus 5.5 System Card · adaptive thinking · max effort unless stated · raw · 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.74.2%
4Claude Opus 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · raw · 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.73.4%
5Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · raw · no tools · Opus 4.8 grader · max · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71%
6GPT-6 Astraclinical-result-1799· Clinical Benchmarks data docs70.3%
7Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.2%
8Claude Sonnet 5.5clinical-result-1800· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim69.2%
9Claude Sonnet 5.5length-adjusted · no tools · Opus 4.8 grader · max · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.2%
10Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.7%
11GPT-6.1 SolGPT-6.1 Sol system card · unadjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.2%
12GPT-6.2 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.3%
13Claude Fable 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66%
14Claude Fable 5clinical-result-204· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim66%
15Claude Fable 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.66%
16GPT-6.2 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.9%
17Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.6%
18Claude Opus 5.5clinical-result-1801· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim65.6%
19Claude Opus 5.5Opus 5.5 System Card · adaptive thinking · max effort unless stated · length-adjusted · no tools · Opus 4.8 grader · max · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.6%
20GPT-6 Lunaclinical-result-2378· Clinical Benchmarks data docs65.5%
21Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.8%
22Claude Haiku 5.5clinical-result-2364· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim64.8%
23Claude Haiku 5.5length-adjusted · no tools · Opus 4.8 grader · max · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.8%
24GPT-6 Astraclinical-result-563· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim64.7%
25GPT-6.1 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.2%
26GPT-6.1 Solclinical-result-2345· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim64.2%
27GPT-6.1 SolGPT-6.1 Sol system card · length-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.2%
28GPT-6 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.4%
29GPT-6 Astralength-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.4%
30GPT-6 Astralength-adjusted score · rejected requests scored zero · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.4%
31Claude Fable 5clinical-result-1870· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim63.3%
32Claude Fable 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.63.3%
33GPT-6.1 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.7%
34GPT-6.1 Terraclinical-result-2399· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim62.7%
35Claude Sonnet 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · raw · 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.62.4%
36Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.3%
37Muse Wonder Fullclinical-result-2404· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim62.3%
38Claude Fable 5.1clinical-result-561· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim62.1%
39Claude Fable 5.1length-adjusted score · rejected requests scored zero · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62.1%
40Claude Fable 5.1Opus 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.62.1%
41Claude Fable 5.1System 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.62.1%
42Claude Fable 5length-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.9%
43Claude Fable 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.60.9%
44GPT-6 Lunaclinical-result-1803· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim60.8%
45GPT-6 Solclinical-result-1802· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim60.8%
46GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
47GPT-5.6 Solclinical-result-205· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
48GPT-5.6 Sollength-adjusted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.5%
49GPT-5.6 Sollength-adjusted score · rejected requests scored zero · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.5%
50GPT-5.6 SolOpenAI 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.60.5%

Showing 1–50 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