HealthBench Professional

OpenAI logoGPT-6.1 Terra on HealthBench Professional

Rank 10 of 43, updated November 2, 2026.

GPT-6.1 Terra scores 0.627 on HealthBench Professional, rank 10 of 43 models on the board. HealthBench Professional scores models on 525 tasks drawn from real clinician conversations, graded criterion by criterion against physician-written rubrics on a 0 to 1 scale.

10
rank of 43
0.627
length-adjusted score
0.642
score before the length adjustment
0.076
gap to the leader, GPT-6 Astra (Anthropic run)
1.05M
context window, tokens
$1.00 / $5.00
input / output price per 1M tokens

Where it sits on the board

The models ranked around GPT-6.1 Terra, by length-adjusted score. Differences are against GPT-6.1 Terra.

RankModelLength-adjustedBefore the adjustmentDifference
7OpenAI logoGPT-6 Astra0.6470.682+0.020
8OpenAI logoGPT-6.1 Sol0.6420.672+0.015
9Anthropic logoClaude Fable 5 (September card)0.6330.689+0.006
10OpenAI logoGPT-6.1 Terra0.6270.642–
11Meta logoMuse Wonder Full0.623–-0.004
12Anthropic logoClaude Fable 5.10.6210.742-0.006
13OpenAI logoGPT-6 Luna0.6080.612-0.019

Result and API facts

Rank10 of 43
Length-adjusted score0.627
Score before the length adjustment0.642
LabOpenAI
Context window1.05M tokens
API price per 1M tokens$1.00 in / $5.00 out
Licenseproprietary
SourceAddendum to GPT-6 Astra System Card: GPT-6.1 Terra (system card)
Released2026-10-26

Source of this score

Read from Addendum to GPT-6 Astra System Card: GPT-6.1 Terra (system card, OpenAI, 2026-10-26). Vendor-reported. Confidence: verified. Configuration: 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.

Section 5.1, Table 5, HealthBench Professional length-adjusted, GPT-6.1 Terra columnfull entry on the sources page
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)

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.076. Directly above sits Claude Fable 5 (September card) at 0.633. Directly below sits Muse Wonder Full at 0.623. The scores on this page are compiled from published documents rather than from one controlled run, so a small gap between 2 models can reflect a difference in grader version, reasoning effort, or deployment setting as well as a difference in capability.

What does GPT-6.1 Terra score on HealthBench Professional?

GPT-6.1 Terra scores 0.627 on HealthBench Professional, which places it at rank 10 of 43 models on the board as of November 2, 2026. The number was read from Addendum to GPT-6 Astra System Card: GPT-6.1 Terra, listed on the sources page.

How much does GPT-6.1 Terra cost to run?

GPT-6.1 Terra is priced at $1.00 per million input tokens and $5.00 per million output tokens through OpenAI's API.

Pairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.

  • GPT-6.1 Terra vs GPT-6 Astra (Anthropic run)
    0.627 vs 0.703, GPT-6 Astra (Anthropic run) by 0.076
  • GPT-6.1 Terra vs Claude Sonnet 5.5
    0.627 vs 0.692, Claude Sonnet 5.5 by 0.065
  • GPT-6.1 Terra vs Claude Fable 5
    0.627 vs 0.660, Claude Fable 5 by 0.033
  • GPT-6.1 Terra vs Claude Opus 5.5
    0.627 vs 0.656, Claude Opus 5.5 by 0.029
  • GPT-6.1 Terra vs GPT-6 Luna (Anthropic run)
    0.627 vs 0.655, GPT-6 Luna (Anthropic run) by 0.028
  • GPT-6.1 Terra vs Claude Haiku 5.5
    0.627 vs 0.648, Claude Haiku 5.5 by 0.021
  • GPT-6.1 Terra vs GPT-6 Astra
    0.627 vs 0.647, GPT-6 Astra by 0.020
  • GPT-6.1 Terra vs GPT-6.1 Sol
    0.627 vs 0.642, GPT-6.1 Sol by 0.015
  • GPT-6.1 Terra vs Claude Fable 5 (September card)
    0.627 vs 0.633, Claude Fable 5 (September card) by 0.006
  • GPT-6.1 Terra vs Muse Wonder Full
    0.627 vs 0.623, GPT-6.1 Terra by 0.004
  • GPT-6.1 Terra vs Claude Fable 5.1
    0.627 vs 0.621, GPT-6.1 Terra by 0.006
  • GPT-6.1 Terra vs GPT-6 Luna
    0.627 vs 0.608, GPT-6.1 Terra by 0.019
  • GPT-6.1 Terra vs GPT-6 Sol
    0.627 vs 0.608, GPT-6.1 Terra by 0.019
  • GPT-6.1 Terra vs GPT-5.6 Sol
    0.627 vs 0.605, GPT-6.1 Terra by 0.022
  • GPT-6.1 Terra vs Muse Wonder
    0.627 vs 0.605, GPT-6.1 Terra by 0.022
  • GPT-6.1 Terra vs Claude Opus 5
    0.627 vs 0.598, GPT-6.1 Terra by 0.029
  • GPT-6.1 Terra vs Muse Spark 1.1
    0.627 vs 0.593, GPT-6.1 Terra by 0.034
  • GPT-6.1 Terra vs Claude Sonnet 5
    0.627 vs 0.578, GPT-6.1 Terra by 0.049
  • GPT-6.1 Terra vs GPT-5.6 Terra
    0.627 vs 0.577, GPT-6.1 Terra by 0.050
  • GPT-6.1 Terra vs Claude Opus 4.8 (Opus 4.8 grader)
    0.627 vs 0.574, GPT-6.1 Terra by 0.053
  • GPT-6.1 Terra vs Grok 4.7
    0.627 vs 0.567, GPT-6.1 Terra by 0.060
  • GPT-6.1 Terra vs Claude Opus 4.8
    0.627 vs 0.558, GPT-6.1 Terra by 0.069
  • GPT-6.1 Terra vs GPT-5.6 Luna
    0.627 vs 0.557, GPT-6.1 Terra by 0.070
  • GPT-6.1 Terra vs Gemini 4 Argon
    0.627 vs 0.551, GPT-6.1 Terra by 0.076
  • GPT-6.1 Terra vs Muse Spark
    0.627 vs 0.541, GPT-6.1 Terra by 0.086
  • GPT-6.1 Terra vs GPT-5.6 Sol (August)
    0.627 vs 0.540, GPT-6.1 Terra by 0.087
  • GPT-6.1 Terra vs Kimi K3
    0.627 vs 0.532, GPT-6.1 Terra by 0.095
  • GPT-6.1 Terra vs GLM 5.3
    0.627 vs 0.528, GPT-6.1 Terra by 0.099
  • GPT-6.1 Terra vs Claude Opus 4.7
    0.627 vs 0.519, GPT-6.1 Terra by 0.108
  • GPT-6.1 Terra vs GPT-5.5
    0.627 vs 0.518, GPT-6.1 Terra by 0.109
  • GPT-6.1 Terra vs Gemini 3.8 Flash
    0.627 vs 0.517, GPT-6.1 Terra by 0.110
  • GPT-6.1 Terra vs DeepSeek V4.1 Flash
    0.627 vs 0.507, GPT-6.1 Terra by 0.120
  • GPT-6.1 Terra vs Grok 4.6
    0.627 vs 0.485, GPT-6.1 Terra by 0.142
  • GPT-6.1 Terra vs GPT-5.4
    0.627 vs 0.481, GPT-6.1 Terra by 0.146
  • GPT-6.1 Terra vs GPT-5
    0.627 vs 0.462, GPT-6.1 Terra by 0.165
  • GPT-6.1 Terra vs GPT-5.2
    0.627 vs 0.459, GPT-6.1 Terra by 0.168
  • GPT-6.1 Terra vs Claude Sonnet 4.6
    0.627 vs 0.442, GPT-6.1 Terra by 0.185
  • GPT-6.1 Terra vs GPT-5.6 Luna (August)
    0.627 vs 0.441, GPT-6.1 Terra by 0.186
  • GPT-6.1 Terra vs GPT-5.1
    0.627 vs 0.396, GPT-6.1 Terra by 0.231
  • GPT-6.1 Terra vs GPT-5.5 Instant
    0.627 vs 0.384, GPT-6.1 Terra by 0.243
  • GPT-6.1 Terra vs MAI-Thinking-1
    0.627 vs 0.350, GPT-6.1 Terra by 0.277
  • GPT-6.1 Terra vs Claude Haiku 4.5
    0.627 vs 0.322, GPT-6.1 Terra by 0.305

Where the scores come from and how they are read is on the methodology page. The full ranking is on the leaderboard.