Skip to content

Benchmark

HealthBench Consensus

Scores are percentages. Higher is better.

Models measured
10
Scores recorded
16
Sources
2
IQ weight
0.00

Score distribution

92.2%
Mean
95.1%
Median
4.6%
Std dev
84.9%
10th percentile
96%
90th percentile
82.6%
Min
82.6%96%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 for chat models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-6.1 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96%
2GPT-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.96%
3GPT-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.95.9%
4GPT 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.95.6%
5GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.5%
6GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.1%
7GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.1%
8GPT-6.1 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.1%
9GPT-5.5 Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.7%
10GPT 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.94.5%
11GPT 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.90.8%
12GPT 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.90.6%
13GPT 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.89.9%
14GPT 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.84.9%
15GPT 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.83%
16GPT 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.82.6%

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