HealthBench Professional

Google logoGemini 4 Argon on HealthBench Professional

Rank 25 of 43, updated November 2, 2026.

Gemini 4 Argon scores 0.551 on HealthBench Professional, rank 25 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.

25
rank of 43
0.551
length-adjusted score
0.642
score before the length adjustment
0.152
gap to the leader, GPT-6 Astra (Anthropic run)
–
context window not published
$2.00 / $10.00
input / output price per 1M tokens

Where it sits on the board

The models ranked around Gemini 4 Argon, by length-adjusted score. Differences are against Gemini 4 Argon.

RankModelLength-adjustedBefore the adjustmentDifference
22SpaceX AI logoGrok 4.70.567–+0.016
23Anthropic logoClaude Opus 4.80.558–+0.007
24OpenAI logoGPT-5.6 Luna0.5570.598+0.006
25Google logoGemini 4 Argon0.5510.642–
26Meta logoMuse Spark0.541–-0.010
27OpenAI logoGPT-5.6 Sol (August)0.5400.566-0.011
28Moonshot AI logoKimi K30.5320.569-0.019

Result and API facts

Rank25 of 43
Length-adjusted score0.551
Score before the length adjustment0.642
LabGoogle
Context windownot published
API price per 1M tokens$2.00 in / $10.00 out
Licenseproprietary
SourceHealthBench Professional Benchmark | Artificial Analysis (independent leaderboard)
Released2026-09-30

Source of this score

Read from HealthBench Professional Benchmark | Artificial Analysis (independent leaderboard, Artificial Analysis, 2026-11-02). Independent run. Confidence: partial. Configuration: 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).

Score section, Length-Adjusted Score chart, Gemini 4 Argon (high) bar label; raw score 64.2% on the Raw Score tabfull entry on the sources page
HealthBench Professional: Length-Adjusted Score | Gemini 4 Argon (high) | 55.1%

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.152. Directly above sits GPT-5.6 Luna at 0.557. Directly below sits Muse Spark at 0.541. 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 Gemini 4 Argon score on HealthBench Professional?

Gemini 4 Argon scores 0.551 on HealthBench Professional, which places it at rank 25 of 43 models on the board as of November 2, 2026. The number was read from HealthBench Professional Benchmark | Artificial Analysis, listed on the sources page.

How much does Gemini 4 Argon cost to run?

Gemini 4 Argon is priced at $2.00 per million input tokens and $10.00 per million output tokens through Google's API.

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

  • Gemini 4 Argon vs GPT-6 Astra (Anthropic run)
    0.551 vs 0.703, GPT-6 Astra (Anthropic run) by 0.152
  • Gemini 4 Argon vs Claude Sonnet 5.5
    0.551 vs 0.692, Claude Sonnet 5.5 by 0.141
  • Gemini 4 Argon vs Claude Fable 5
    0.551 vs 0.660, Claude Fable 5 by 0.109
  • Gemini 4 Argon vs Claude Opus 5.5
    0.551 vs 0.656, Claude Opus 5.5 by 0.105
  • Gemini 4 Argon vs GPT-6 Luna (Anthropic run)
    0.551 vs 0.655, GPT-6 Luna (Anthropic run) by 0.104
  • Gemini 4 Argon vs Claude Haiku 5.5
    0.551 vs 0.648, Claude Haiku 5.5 by 0.097
  • Gemini 4 Argon vs GPT-6 Astra
    0.551 vs 0.647, GPT-6 Astra by 0.096
  • Gemini 4 Argon vs GPT-6.1 Sol
    0.551 vs 0.642, GPT-6.1 Sol by 0.091
  • Gemini 4 Argon vs Claude Fable 5 (September card)
    0.551 vs 0.633, Claude Fable 5 (September card) by 0.082
  • Gemini 4 Argon vs GPT-6.1 Terra
    0.551 vs 0.627, GPT-6.1 Terra by 0.076
  • Gemini 4 Argon vs Muse Wonder Full
    0.551 vs 0.623, Muse Wonder Full by 0.072
  • Gemini 4 Argon vs Claude Fable 5.1
    0.551 vs 0.621, Claude Fable 5.1 by 0.070
  • Gemini 4 Argon vs GPT-6 Luna
    0.551 vs 0.608, GPT-6 Luna by 0.057
  • Gemini 4 Argon vs GPT-6 Sol
    0.551 vs 0.608, GPT-6 Sol by 0.057
  • Gemini 4 Argon vs GPT-5.6 Sol
    0.551 vs 0.605, GPT-5.6 Sol by 0.054
  • Gemini 4 Argon vs Muse Wonder
    0.551 vs 0.605, Muse Wonder by 0.054
  • Gemini 4 Argon vs Claude Opus 5
    0.551 vs 0.598, Claude Opus 5 by 0.047
  • Gemini 4 Argon vs Muse Spark 1.1
    0.551 vs 0.593, Muse Spark 1.1 by 0.042
  • Gemini 4 Argon vs Claude Sonnet 5
    0.551 vs 0.578, Claude Sonnet 5 by 0.027
  • Gemini 4 Argon vs GPT-5.6 Terra
    0.551 vs 0.577, GPT-5.6 Terra by 0.026
  • Gemini 4 Argon vs Claude Opus 4.8 (Opus 4.8 grader)
    0.551 vs 0.574, Claude Opus 4.8 (Opus 4.8 grader) by 0.023
  • Gemini 4 Argon vs Grok 4.7
    0.551 vs 0.567, Grok 4.7 by 0.016
  • Gemini 4 Argon vs Claude Opus 4.8
    0.551 vs 0.558, Claude Opus 4.8 by 0.007
  • Gemini 4 Argon vs GPT-5.6 Luna
    0.551 vs 0.557, GPT-5.6 Luna by 0.006
  • Gemini 4 Argon vs Muse Spark
    0.551 vs 0.541, Gemini 4 Argon by 0.010
  • Gemini 4 Argon vs GPT-5.6 Sol (August)
    0.551 vs 0.540, Gemini 4 Argon by 0.011
  • Gemini 4 Argon vs Kimi K3
    0.551 vs 0.532, Gemini 4 Argon by 0.019
  • Gemini 4 Argon vs GLM 5.3
    0.551 vs 0.528, Gemini 4 Argon by 0.023
  • Gemini 4 Argon vs Claude Opus 4.7
    0.551 vs 0.519, Gemini 4 Argon by 0.032
  • Gemini 4 Argon vs GPT-5.5
    0.551 vs 0.518, Gemini 4 Argon by 0.033
  • Gemini 4 Argon vs Gemini 3.8 Flash
    0.551 vs 0.517, Gemini 4 Argon by 0.034
  • Gemini 4 Argon vs DeepSeek V4.1 Flash
    0.551 vs 0.507, Gemini 4 Argon by 0.044
  • Gemini 4 Argon vs Grok 4.6
    0.551 vs 0.485, Gemini 4 Argon by 0.066
  • Gemini 4 Argon vs GPT-5.4
    0.551 vs 0.481, Gemini 4 Argon by 0.070
  • Gemini 4 Argon vs GPT-5
    0.551 vs 0.462, Gemini 4 Argon by 0.089
  • Gemini 4 Argon vs GPT-5.2
    0.551 vs 0.459, Gemini 4 Argon by 0.092
  • Gemini 4 Argon vs Claude Sonnet 4.6
    0.551 vs 0.442, Gemini 4 Argon by 0.109
  • Gemini 4 Argon vs GPT-5.6 Luna (August)
    0.551 vs 0.441, Gemini 4 Argon by 0.110
  • Gemini 4 Argon vs GPT-5.1
    0.551 vs 0.396, Gemini 4 Argon by 0.155
  • Gemini 4 Argon vs GPT-5.5 Instant
    0.551 vs 0.384, Gemini 4 Argon by 0.167
  • Gemini 4 Argon vs MAI-Thinking-1
    0.551 vs 0.350, Gemini 4 Argon by 0.201
  • Gemini 4 Argon vs Claude Haiku 4.5
    0.551 vs 0.322, Gemini 4 Argon by 0.229

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