Results

6 results

HealthBench HealthBench Hard results
ProviderModelScoreSourceRegistry No.
Meta AI (originally Facebook AI Research)Muse Spark (thinking)42.8%ai.meta.com for Muse Spark (thinking) on HealthBench HealthBench Hard (opens in a new tab)HealthBench ScoreReported Evaluation methodologyMetaSelf-reportedRecord for Muse Spark on HealthBench HealthBench Hard80001
OpenAIOpenAI o3 (high)31.6%deploymentsafety.openai.com for OpenAI o3 (high) on HealthBench HealthBench Hard (opens in a new tab)HealthBench ScoreReported Model cardOpenAISelf-reportedRecord for OpenAI o3 on HealthBench HealthBench Hard10003
OpenAIOpenAI o4-mini (high)17.5%deploymentsafety.openai.com for OpenAI o4-mini (high) on HealthBench HealthBench Hard (opens in a new tab)HealthBench ScoreReported Model cardOpenAISelf-reportedRecord for OpenAI o4-mini on HealthBench HealthBench Hard10004
OpenAIgpt-oss-120b (low)22.8%deploymentsafety.openai.com for gpt-oss-120b (low) on HealthBench HealthBench Hard (opens in a new tab)HealthBench ScoreReported Model cardOpenAISelf-reportedRecord for gpt-oss-120b on HealthBench HealthBench Hard15001
OpenAIgpt-oss-120b (medium)26.9%deploymentsafety.openai.com for gpt-oss-120b (medium) on HealthBench HealthBench Hard (opens in a new tab)HealthBench ScoreReported Model cardOpenAISelf-reportedRecord for gpt-oss-120b on HealthBench HealthBench Hard15001
OpenAIgpt-oss-120b (high)30.0%deploymentsafety.openai.com for gpt-oss-120b (high) on HealthBench HealthBench Hard (opens in a new tab)HealthBench ScoreReported Model cardOpenAISelf-reportedRecord for gpt-oss-120b on HealthBench HealthBench Hard15001