Sources
This page lists the document behind each score on the leaderboard. Arcophos does not run HealthBench Professional; the numbers are copied from vendor system cards, official update reports, model cards, launch announcements, and named leaderboards, exactly as those documents print them. Entries are grouped by document. Each one gives the model, the score as printed, the excerpt the number was read from, where it sits in the document, who reported it, and a confidence label. Rows with no located document are listed at the end rather than left out. How the labels are assigned and why 2 documents can disagree is on the methodology page.
Addendum to GPT-6 Astra System Card: GPT-6.1 Sol
system card, first party. OpenAI. deploymentsafety.openai.com. Published September 29, 2026. Retrieved October 6, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6.1 Sol | 64.2 | 0.672 | primary sourcevendor-reportedverified OpenAI; length-adjusted; 64.2 (67.2, 3038) (adjusted, raw, mean response characters); addendum Table 7 refers to the GPT-6 Astra card for method | EVALUATION | GPT-5.5 | GPT-5.6 SOL | GPT-5.6 TERRA | GPT-5.6 LUNA | GPT-6 ASTRA | GPT-6 SOL | GPT-6 LUNA | GPT-6.1 SOL HealthBench Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119) | 64.2 (67.2, 3038) |
Addendum to GPT-6 Astra System Card: GPT-6.1 Terra
system card, first party. OpenAI. deploymentsafety.openai.com. Published October 26, 2026. Retrieved November 2, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6.1 Terra | 62.7 | 0.642 | primary sourcevendor-reportedverified OpenAI; length-adjusted; 62.7 (64.2, 2531) (adjusted, raw, mean response characters); addendum Table 5 refers to the GPT-6 Astra card for method | EVALUATION GPT-5.5 GPT-5.6-SOL GPT-5.6-TERRA GPT-5.6-LUNA GPT-6 ASTRA GPT-6-SOL GPT-6-LUNA GPT-6.1-SOL GPT-6.1-TERRA HealthBench Professional length-adjusted 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) 64.7 (68.2, 3185) 60.8 (59.5, 1573) 60.8 (61.2, 2119) 64.2 (67.2, 3038) 62.7 (64.2, 2531) |
Claude Fable 5 and Claude Mythos 5 System Card
system card, first party. Anthropic. anthropic.com. Published June 9, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Claude Fable 5 | 66.0 | 0.703 | primary sourcevendor-reportedverified length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 70.3%). Measured as Claude Mythos 5; Anthropic itself prints 66.0 in the Fable 5 column of the Opus 5 card with footnote Mythos 5. | HealthBench Professional 66.0 - 64.7 56.9 51.8 - |
| Claude Opus 4.8 | 56.9 | – | conflicting | HealthBench Professional 66.0 - 64.7 56.9 51.8 - |
Claude Fable 5.1 and Claude Mythos 5.1 System Card
system card, first party. Anthropic. anthropic.com.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Claude Fable 5 | 63.3% | – | conflicting | HealthBench Professional 62.1% 63.3% 59.8% – |
| Claude Fable 5 (September card) | 63.3% | 0.689 | primary sourcevendor-reportedverified Measured as Claude Fable 5; Anthropic September card; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt; raw 68.9% | HealthBench Professional | Length-adjusted score | Claude Fable 5 | 63.3% |
| Claude Fable 5.1 | 62.1% | 0.742 | primary sourcevendor-reportedverified length-adjusted (method published in the HealthBench Professional paper); Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over five trials, no tools or customized system prompt; Fable 5.1 run with safety classifiers active and a refusal-fallback to Claude Opus 5 (raw 74.2%). | On HealthBench Professional, Claude Fable 5.1 achieved a raw score of 74.2%, ahead of Claude Opus 5 at 73.4%, Fable 5 at 68.9%, and Claude Sonnet 5 at 62.4%. After length adjustment, which penalizes verbose model responses, Fable 5.1 achieved a score of 62.1%. |
| Claude Opus 5 | 59.8% | – | corroborating | HealthBench Professional 62.1% 63.3% 59.8% – |
Claude Haiku 5.5 System Card
system card, first party. Anthropic. anthropic.com. Published October 7, 2026. Retrieved October 12, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6 Luna (Anthropic run) | 65.5% | not printed in the source | primary sourceindependent runverified Run by Anthropic through OpenAI's public API; max effort; Opus 4.8 grader; length-adjusted; not OpenAI's published figure | HealthBench Professional panel: 65.5% (GPT-6 Luna (OpenAI)); caption: GPT-6 Luna's scores come from our own runs through OpenAI's public API and are not OpenAI's published figures. |
| Claude Haiku 5.5 | 64.8% | 0.710 | primary sourcevendor-reportedverified Anthropic; max effort; Opus 4.8 grader; safety classifiers enabled; length-adjusted; raw 71.0%; five runs (October 1 and 2); thirteen repeat max runs on October 4 averaged 64.2% | Max effort scored highest, at 64.8% (71.0% raw); thirteen repeat runs at max on October 4, the day of the lower levels, averaged 64.2%. |
| Claude Haiku 4.5 | 32.2 | not printed in the source | primary sourcevendor-reportedverified Anthropic; extended thinking (Haiku 4.5 has no effort setting); Opus 4.8 grader; safety classifiers enabled; length-adjusted; measured for the Haiku 5.5 card | Evaluation | Haiku 5.5 | Haiku 4.5 | Sonnet 5.5 | GPT-6 Luna HealthBench Professional (Length-adjusted) | 64.8 | 32.2 | 69.2 | – |
Claude Opus 5.5 System Card
system card, first party. Anthropic. anthropic.com. Published September 22, 2026. Retrieved November 1, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Claude Opus 5.5 | 65.6% | 0.771 | primary sourcevendor-reportedverified Anthropic; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt; safety classifiers and refusal fallback to Opus 5; length-adjusted; raw 77.1% | 8.15.2 HealthBench Professional results length adjustment, which penalizes verbose model responses, Claude Opus 5.5 achieved a score of 65.6%. |
Claude Sonnet 5.5 System Card
system card, first party. Anthropic. anthropic.com. Published September 28, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6 Astra (Anthropic run) | 70.3% | 0.740 | primary sourceindependent runverified Anthropic public-API reproduction; max effort; no system prompt; Opus 4.8 grader; length-adjusted; raw 74.0% | On HealthBench Professional at max effort, length adjustment changes the ranking. After: GPT-6 Astra (70.3%) > Claude Sonnet 5.5 (69.2%) > Claude Opus 5.5 (65.6%) > Claude Fable 5.1 (62.1%). |
| Claude Sonnet 5.5 | 69.2% | 0.771 | primary sourcevendor-reportedverified Anthropic; max effort; Opus 4.8 grader; safety classifiers enabled; length-adjusted; raw 77.1% | On HealthBench Professional at max effort, length adjustment changes the ranking. After: GPT-6 Astra (70.3%) > Claude Sonnet 5.5 (69.2%) > Claude Opus 5.5 (65.6%) > Claude Fable 5.1 (62.1%). |
GPT-5.5 Instant System Card
system card, first party. OpenAI. deploymentsafety.openai.com. Published May 5, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-5.5 Instant | 38.4 | 0.407 | primary sourcevendor-reportedverified length-adjusted (40.7 unadjusted, 2,775 mean response chars); GPT-5.5 Instant system card Table 5, column GPT-5.5 INSTANT. | HealthBench Professional 37.6 (40.4, 2,973) 35.7 (38.3, 2,872) 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) |
GPT-5.6 - August Updates (system card addendum)
system card, first party. OpenAI. cdn.openai.com. Published August 6, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-5.6 Sol (August) | 54.0 | 0.566 | primary sourcevendor-reportedverified ChatGPT production (Instant) deployment setting, length-adjusted, GPT-5.6 August Updates PDF column GPT-5.6 Sol (August) (56.6 unadjusted, 2,894 chars) | HealthBench Professional 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) 54.0 (56.6, 2,894) 44.1 (46.8, 2,920) |
| GPT-5.6 Luna (August) | 44.1 | 0.468 | primary sourcevendor-reportedverified ChatGPT production (Instant) deployment setting, length-adjusted, GPT-5.6 August Updates PDF column GPT-5.6 Luna (August) (46.8 unadjusted, 2,920 chars) | HealthBench Professional 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) 54.0 (56.6, 2,894) 44.1 (46.8, 2,920) |
| GPT-5.5 Instant | 38.4 | – | corroborating | HealthBench Professional 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) 54.0 (56.6, 2,894) 44.1 (46.8, 2,920) |
GPT-5.6 Preview System Card
system card, first party. OpenAI. deploymentsafety.openai.com.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-5.6 Sol | 60.5 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.6 Terra | 57.7 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.6 Luna | 55.7 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.5 | 51.8 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.4 | 48.1 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5 | 46.2 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.2 | 45.9 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.1 | 39.6 | – | corroborating | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
GPT-5.6 System Card
system card, first party. OpenAI. deploymentsafety.openai.com. Published July 9, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-5.6 Sol | 60.5 | 0.641 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort (64.1 unadjusted, 3,228 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-SOL. API max-effort setting, not the August ChatGPT production setting measured in row 492. | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.6 Terra | 57.7 | 0.624 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort (62.4 unadjusted, 3,618 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-TERRA. | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.6 Luna | 55.7 | 0.598 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort (59.8 unadjusted, 3,389 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-LUNA. API max-effort setting, not the August ChatGPT production setting measured in row 493. | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.5 | 51.8 | 0.572 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.5 (57.2 unadjusted, 3818 chars) | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.4 | 48.1 | 0.519 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.4 (51.9 unadjusted, 3308 chars) | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5 | 46.2 | 0.510 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5 (51.0 unadjusted, 3616 chars) | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.2 | 45.9 | 0.500 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.2 (50.0 unadjusted, 3400 chars) | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
| GPT-5.1 | 39.6 | 0.480 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.1 (48.0 unadjusted, 4863 chars) | HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) |
GPT-6 Astra System Card
system card, first party. OpenAI. deploymentsafety.openai.com.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6 Astra | 63.4 | – | conflicting | Astra has a length-adjusted HealthBench Professional score of 63.4 (+2.9 relative to GPT-5.6 Sol), HealthBench score of 58.1 (+1.1), HealthBench Hard score of 36.3 (+3.2), and HealthBench Consensus score of 95.8 (+0.3). |
GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)
system card, first party. OpenAI. deploymentsafety.openai.com. Published September 3, 2026. Retrieved September 8, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6 Astra | 64.7 | 0.682 | primary sourcevendor-reportedverified length-adjusted, max reasoning effort (68.2 unadjusted, 3,185 mean response chars, as corrected by OpenAI on September 22; first printed as 69.5 and 4,097); GPT-6 Astra system card Table 6, column 'gpt-6 Astra'. | Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119) |
| GPT-6 Astra | 63.4 | – | mirror | Astra has a length-adjusted HealthBench Professional score of 63.4 (+2.9 relative to GPT-5.6 Sol) |
| GPT-6 Luna | 60.8 | 0.612 | primary sourcevendor-reportedverified OpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters) | Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119) |
| GPT-6 Sol | 60.8 | 0.595 | primary sourcevendor-reportedverified OpenAI; length-adjusted; maximum reasoning effort; 60.8 (59.5, 1573) (adjusted, raw, mean response characters) | Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119) |
GPT-6 Astra: A new generation of intelligence
launch post, first party. OpenAI. openai.com.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| GPT-6 Astra | 63.4% | – | corroborating | | HealthBench Professional (length-adjusted) | 63.4% | 60.5% | 58.1% | 60.9% | 56.4% | 52.1% | |
HealthBench Professional Benchmark | Artificial Analysis
independent leaderboard. Artificial Analysis. artificialanalysis.ai. Published November 2, 2026. Retrieved November 2, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Gemini 4 Argon | 55.1% | 0.642 | primary sourceindependent runpartial Artificial Analysis independent run, high reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (64.2 raw, 5,133 mean response chars) | HealthBench Professional: Length-Adjusted Score | Gemini 4 Argon (high) | 55.1% |
| Kimi K3 | 53.2% | 0.569 | primary sourceindependent runpartial Artificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (56.9 raw, 3,250 mean response chars) | HealthBench Professional: Length-Adjusted Score | Kimi K3 (max) | 53.2% |
| GLM 5.3 | 52.8% | 0.579 | primary sourceindependent runpartial Artificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (57.9 raw, 3,748 mean response chars) | HealthBench Professional: Length-Adjusted Score | GLM-5.3 (max) | 52.8% |
| Gemini 3.8 Flash | 51.7% | 0.590 | primary sourceindependent runpartial Artificial Analysis independent run, high reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (59.0 raw, 4,494 mean response chars) | HealthBench Professional: Length-Adjusted Score | Gemini 3.8 Flash (high) | 51.7% |
| DeepSeek V4.1 Flash | 50.7% | 0.529 | primary sourceindependent runpartial Artificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (52.9 raw, 2,760 mean response chars) | HealthBench Professional: Length-Adjusted Score | DeepSeek V4.1 Flash (max) | 50.7% |
Introducing Grok 4.7
launch post, first party. SpaceXAI. x.ai. Published September 21, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Grok 4.7 | 56.7% | not printed in the source | primary sourcevendor-reportedverified SpaceXAI evaluation; xHigh effort; HealthBench Professional | Grok 4.7 xHigh Grok 4.6 High GPT-5.6 Sol Max Fable 5.1 Max Clinical reasoningHealthBench Professional 56.7% 48.5% 60.5% 62.1% |
| Grok 4.6 | 48.5% | not printed in the source | primary sourcevendor-reportedverified SpaceXAI evaluation; High effort; HealthBench Professional | Grok 4.7 xHigh Grok 4.6 High GPT-5.6 Sol Max Fable 5.1 Max Clinical reasoningHealthBench Professional 56.7% 48.5% 60.5% 62.1% |
MAI-Thinking-1: Building a Hill-Climbing Machine
model card, first party. Microsoft AI. microsoft.ai. Published August 12, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| MAI-Thinking-1 | 35 | not printed in the source | primary sourcevendor-reportedverified length-adjusted (HealthBench Professional length penalty), standard GPT-5.4 grader and OpenAI rubrics, Microsoft AI run; printed at integer precision. | Model AIR-Bench CyberSec Instruct CyberSec Auto Long Fact Truthful QA HealthBench Prof. MedXpert QA MAI-Thinking-1 88 63 63 98 88 35 43 Sonnet 4.6 88 62 56 98 88 38 49 |
Muse Spark 1.1 Evaluation Report
model card, first party. Meta. research.meta.ai. Published July 9, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Muse Spark 1.1 | 59.3 | not printed in the source | primary sourcevendor-reportedverified length-normalized, GPT-5.4 low-reasoning grader, xhigh reasoning via Meta Model API (Muse Spark 1.1 Evaluation Report Figure 44) | Health | HealthBench Professional | 59.3 | 54.1 | 41.6 | 55.8 | 51.8 (Figure 44 image table row; columns Muse Spark 1.1, Muse Spark, Gemini 3.1 Pro (high), Opus 4.8 (max), GPT 5.5 (xhigh)) |
| Muse Spark | 54.1 | not printed in the source | primary sourcevendor-reportedverified length-normalized, GPT-5.4 low-reasoning grader; Muse Spark (1.0) column in the Muse Spark 1.1 Evaluation Report Figure 44 | Health | HealthBench Professional | 59.3 | 54.1 | 41.6 | 55.8 | 51.8 (Figure 44 image table row; columns Muse Spark 1.1, Muse Spark, Gemini 3.1 Pro (high), Opus 4.8 (max), GPT 5.5 (xhigh)) |
Muse Wonder Model Card
model card, first party. Meta. research.meta.ai. Published October 12, 2026. Retrieved November 2, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Muse Wonder Full | 62.3 | not printed in the source | primary sourcevendor-reportedverified Meta internal run; length-normalized weighted rubric score, GPT-5.4 grader, no tools, max reasoning effort (Muse Wonder Model Card p. 3 table, Muse Wonder Full (max) column) | HealthBench Pro (Open-ended health queries) | Muse Wonder Full (max) 62.3 | Muse Wonder (max) 60.5 | Claude Fable 5.1 (max) 62.1 | GPT-6 Astra (max) 65.3 | Claude Opus 5.5 (max) 65.6 Methodology (p. 4): HealthBench Pro evaluates responses to 525 professional-grade health questions. Models answer without tools, and a GPT-5.4 grader scores each response against physician-written rubrics. We run the official tasks and grading in a common internal framework. The primary metric is the length-normalized weighted rubric score. |
| Muse Wonder | 60.5 | not printed in the source | primary sourcevendor-reportedverified Meta internal run; length-normalized weighted rubric score, GPT-5.4 grader, no tools, max reasoning effort (Muse Wonder Model Card p. 3 table, Muse Wonder (max) column) | HealthBench Pro (Open-ended health queries) | Muse Wonder Full (max) 62.3 | Muse Wonder (max) 60.5 | Claude Fable 5.1 (max) 62.1 | GPT-6 Astra (max) 65.3 | Claude Opus 5.5 (max) 65.6 Methodology (p. 4): HealthBench Pro evaluates responses to 525 professional-grade health questions. Models answer without tools, and a GPT-5.4 grader scores each response against physician-written rubrics. We run the official tasks and grading in a common internal framework. The primary metric is the length-normalized weighted rubric score. |
System Card: Claude Opus 4.8
system card, first party. Anthropic. anthropic.com. Published May 28, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Claude Opus 4.8 | 55.8% | not printed in the source | primary sourcevendor-reportedverified length-adjusted, adaptive thinking at max effort, Claude Sonnet 4.6 grader (the grader used by the Opus 4.8 card itself); the other Claude rows on this board use the Claude Opus 4.8 grader, under which Anthropic later prints 57.4 for this model. | Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%. |
| Claude Opus 4.7 | 51.9% | not printed in the source | primary sourcevendor-reportedverified length-adjusted; adaptive thinking at max effort; Claude Sonnet 4.6 grader; 5 trials; comparison model in the Opus 4.8 card | Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%. |
| Claude Sonnet 4.6 | 41.7% | – | conflicting | Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%. |
System Card: Claude Opus 5
system card, first party. Anthropic. anthropic.com.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Claude Fable 5 | 66.0 | – | corroborating | HealthBench Professional 59.8 57.4 66.011 60.5 |
| Claude Opus 5 | 59.8% | 0.734 | primary sourcevendor-reportedverified length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 73.4%). | Claude Opus 5 achieved a raw score of 73.4%, which is the highest amongst all Claude models, ahead of Claude Mythos 5 at 70.3%, Claude Opus 4.8 at 60.3%, and Claude Sonnet 5 at 62.4%. After length adjustment, which penalizes verbose model responses, Claude Opus 5 achieved a score of 59.8%. |
| Claude Sonnet 5 | 57.8% | – | corroborating | Figure 8.15.2.A bar labels: Claude Sonnet 5 62.4% raw / 57.8% length-adjusted (prose: 'Claude Sonnet 5 at 62.4%') |
| Claude Opus 4.8 | 57.4 | – | conflicting | HealthBench Professional 59.8 57.4 66.011 60.5 |
System Card: Claude Sonnet 5
system card, first party. Anthropic. anthropic.com. Published June 30, 2026. Retrieved September 7, 2026.
| Model | Length-adjusted score | Score before the length adjustment | Source details | Excerpt and locator |
|---|---|---|---|---|
| Claude Sonnet 5 | 57.8 | 0.624 | primary sourcevendor-reportedverified length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 62.4%). | HealthBench Professional 57.8 44.2 51.8 - |
| Claude Opus 4.8 (Opus 4.8 grader) | 57.4% | not printed in the source | primary sourcevendor-reportedverified Anthropic June evaluation; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt | HealthBench Professional | Length-adjusted score (%) | Claude Opus 4.8 | 57.4% |
| Claude Sonnet 4.6 | 44.2 | not printed in the source | primary sourcevendor-reportedverified length-adjusted; Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt; comparison column in the Sonnet 5 card. Other Anthropic prints: 44.4% (Fable card Figure 8.18.2.A), 41.7% (Opus 4.8 card, Sonnet 4.6 grader) | HealthBench Professional 57.8 44.2 51.8 - |