Skip to content

Benchmark

HealthBench

Scores are percentages. Higher is better.

Models measured
24
Scores recorded
45
Sources
2
IQ weight
2.12

Score distribution

56.7%
Mean
58%
Median
7.5%
Std dev
42.5%
10th percentile
65.4%
90th percentile
30%
Min
30%69.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.12 for chat models, measured over 22 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 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.69.4%
2Claude 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.68.1%
3Claude 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.67.1%
4Claude 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.66.7%
5Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.4%
6GPT 5.2GPT-5.2 Thinking · system-card implementation · raw score· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.3%
7Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.6%
8Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · length-adjusted · max effort · 5-run mean· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.61.6%
9Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · length-adjusted · xhigh effort · single run· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.61.1%
10Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.6%
11Claude 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.60.6%
12Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · length-adjusted · high effort · single run· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.3%
13Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · length-adjusted · medium effort · single run· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.2%
14Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.2%
15Qwen3.8 MaxQwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.2%
16Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · length-adjusted · low effort · single run· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.9%
17Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.6%
18Claude 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.59.3%
19Claude 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.59.2%
20Claude 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.58.7%
21GPT-6.1 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.5%
22GPT-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.58.5%
23Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58%
24GPT OSS 120Bofficial model card Table 3 · reasoning high · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.6%
25GPT OSS 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.6%
26GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57%
27GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57%
28GPT-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.56.7%
29GPT 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.56.5%
30GPT 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.56.5%
31GPT OSS 120Bofficial model card Table 3 · reasoning medium · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.9%
32GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.8%
33GPT-5.6 SolQwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.3%
34GPT-6.1 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.1%
35Qwen3.7 MaxQwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.5%
36GPT-5.3 Chatlatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.1%
37GPT OSS 120Bofficial model card Table 3 · reasoning low · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53%
38Claude Opus 4.8Qwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.4%
39GPT-5.5 Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.4%
40Claude Sonnet 4.6length-adjusted · Opus 4.8 grader · no tools · Sonnet 5 card rerun· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.9%
41GPT OSS 20b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.5%
42GPT OSS 20bofficial model card Table 3 · reasoning high · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.42.5%
43GPT OSS 20bofficial model card Table 3 · reasoning medium · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.41.8%
44GPT OSS 20bofficial model card Table 3 · reasoning low · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.40.4%
45Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim30%

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. · Data by LLM Stats