BlogLLM Benchmark Scores as Published, Side by Side
HealthBench: Results as Published
Every result the catalog holds for HealthBench: 26 models from 5 developers, read from 10 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area HealthcareMaintainer OpenAIIntroduced 2025Data version 2026103001, as of 2026-10-30
HealthBench tests how well an AI model answers health conversations, such as those with patients or clinicians, judged against detailed rubrics written by physicians. It has 5,000 multi-turn conversations and 48,562 rubric criteria, each with a weight that reflects how much a physician would value it. An automatic grader scores each reply against the rubric, and the benchmark includes subsets named Consensus and Hard.
HealthBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 55.1 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 58.5 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 54.5 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 52.1 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 58.3 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 55.8 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 57 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 3 more pages | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 57 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.5OpenAI, released 2026-04-23 | 56.5 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5OpenAI, released 2025-08-07 | 54.3 | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 1 more page | Effort: none |
| 67.2 | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high | |
| o3OpenAI, released 2025-04-16 | 59.8 | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| GPT-4oOpenAI, released 2024-05-13 | 32 | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| GPT-5.5 InstantOpenAI | 51.4 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 59.9 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Effort: low |
| 61.6 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Effort: max | |
| 60.2 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Effort: medium | |
| 60.3 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Effort: high | |
| 61.1 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Effort: xhigh | |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 60.6 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 60 | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25 | - |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 52.4 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 44.2 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Effort: thinking; Tools: none |
| DeepSeek-V3.2-ExpDeepSeek, released 2025-09-29 | 46.9 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 60.2 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.7-MaxAlibaba | 54.5 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Kimi K2 ThinkingMoonshot AI, released 2025-11-06 | 58 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Effort: thinking; Tools: none |
| Kimi K2 Instruct 0905Moonshot AI, released 2025-09-05 | 43.8 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
HealthBench (unadjusted)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 51.1 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 56.7 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 50 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 55.7 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 56.9 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 55.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 55.6 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 58.7 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 58.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.5 InstantOpenAI | 50.9 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 68.1 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | Effort: max |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 66.7 | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25; printed on 1 more page | Effort: max |
| Claude Opus 5Anthropic, released 2026-07-24 | 67.1 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 1 more page | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 59.2 | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25; printed on 1 more page | - |
| Claude Fable 5Anthropic, released 2026-06-09 | 61.2 | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25 | - |
HealthBench Hard
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 31.4 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 36.2 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 31.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 27.8 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 36.6 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 32 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 33.1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 32.7 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.5OpenAI, released 2026-04-23 | 31.5 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5OpenAI, released 2025-08-07 | 46.2 | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| 25.5 | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: none | |
| o3OpenAI, released 2025-04-16 | 31.6 | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| GPT-4oOpenAI, released 2024-05-13 | 0 | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| GPT-5.5 InstantOpenAI | 22.9 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
HealthBench Consensus (length-adjusted)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 95.1 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 96 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 95.9 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 93.8 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 95.5 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 95.1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 95.5 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 95.1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.5OpenAI, released 2026-04-23 | 95.6 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.5 InstantOpenAI | 94.7 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
HealthBench Consensus (unadjusted)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 94.8 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 95.9 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 95.6 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 94 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 95.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 95.1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 95.3 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 95.2 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 95.7 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.5 InstantOpenAI | 94.6 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
HealthBench Hard (unadjusted)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 26 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 33.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 25.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 30.9 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 34.2 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 31.4 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 31.1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 34.3 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 33.8 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.5 InstantOpenAI | 21.3 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
HealthBench Hard (hallucination rate)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5OpenAI, released 2025-08-07 | 1.6% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| 3.6% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: none | |
| o3OpenAI, released 2025-04-16 | 12.9% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| GPT-4oOpenAI, released 2024-05-13 | 15.8% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.