HealthBench Professional

Google logoGemini 3.8 Flash on HealthBench Professional

Rank 32 of 43, updated November 2, 2026.

Gemini 3.8 Flash scores 0.517 on HealthBench Professional, rank 32 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.

32
rank of 43
0.517
length-adjusted score
0.590
score before the length adjustment
0.186
gap to the leader, GPT-6 Astra (Anthropic run)
1M
context window, tokens
$0.75 / $3.75
input / output price per 1M tokens

Where it sits on the board

The models ranked around Gemini 3.8 Flash, by length-adjusted score. Differences are against Gemini 3.8 Flash.

RankModelLength-adjustedBefore the adjustmentDifference
29Zhipu logoGLM 5.30.5280.579+0.011
30Anthropic logoClaude Opus 4.70.519–+0.002
31OpenAI logoGPT-5.50.5180.572+0.001
32Google logoGemini 3.8 Flash0.5170.590–
33DDeepSeek V4.1 Flash0.5070.529-0.010
34SpaceX AI logoGrok 4.60.485–-0.032
35OpenAI logoGPT-5.40.4810.519-0.036

Result and API facts

Rank32 of 43
Length-adjusted score0.517
Score before the length adjustment0.590
LabGoogle
Context window1M tokens
API price per 1M tokens$0.75 in / $3.75 out
Licenseproprietary
SourceHealthBench Professional Benchmark | Artificial Analysis (independent leaderboard)
Released2026-09-02

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 (59.0 raw, 4,494 mean response chars).

Score section, Length-Adjusted Score chart, Gemini 3.8 Flash (high) bar label; raw score 59.0% on the Raw Score tabfull entry on the sources page
HealthBench Professional: Length-Adjusted Score | Gemini 3.8 Flash (high) | 51.7%

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.186. Directly above sits GPT-5.5 at 0.518. Directly below sits DeepSeek V4.1 Flash at 0.507. 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 3.8 Flash score on HealthBench Professional?

Gemini 3.8 Flash scores 0.517 on HealthBench Professional, which places it at rank 32 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 3.8 Flash cost to run?

Gemini 3.8 Flash is priced at $0.75 per million input tokens and $3.75 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 3.8 Flash vs GPT-6 Astra (Anthropic run)
    0.517 vs 0.703, GPT-6 Astra (Anthropic run) by 0.186
  • Gemini 3.8 Flash vs Claude Sonnet 5.5
    0.517 vs 0.692, Claude Sonnet 5.5 by 0.175
  • Gemini 3.8 Flash vs Claude Fable 5
    0.517 vs 0.660, Claude Fable 5 by 0.143
  • Gemini 3.8 Flash vs Claude Opus 5.5
    0.517 vs 0.656, Claude Opus 5.5 by 0.139
  • Gemini 3.8 Flash vs GPT-6 Luna (Anthropic run)
    0.517 vs 0.655, GPT-6 Luna (Anthropic run) by 0.138
  • Gemini 3.8 Flash vs Claude Haiku 5.5
    0.517 vs 0.648, Claude Haiku 5.5 by 0.131
  • Gemini 3.8 Flash vs GPT-6 Astra
    0.517 vs 0.647, GPT-6 Astra by 0.130
  • Gemini 3.8 Flash vs GPT-6.1 Sol
    0.517 vs 0.642, GPT-6.1 Sol by 0.125
  • Gemini 3.8 Flash vs Claude Fable 5 (September card)
    0.517 vs 0.633, Claude Fable 5 (September card) by 0.116
  • Gemini 3.8 Flash vs GPT-6.1 Terra
    0.517 vs 0.627, GPT-6.1 Terra by 0.110
  • Gemini 3.8 Flash vs Muse Wonder Full
    0.517 vs 0.623, Muse Wonder Full by 0.106
  • Gemini 3.8 Flash vs Claude Fable 5.1
    0.517 vs 0.621, Claude Fable 5.1 by 0.104
  • Gemini 3.8 Flash vs GPT-6 Luna
    0.517 vs 0.608, GPT-6 Luna by 0.091
  • Gemini 3.8 Flash vs GPT-6 Sol
    0.517 vs 0.608, GPT-6 Sol by 0.091
  • Gemini 3.8 Flash vs GPT-5.6 Sol
    0.517 vs 0.605, GPT-5.6 Sol by 0.088
  • Gemini 3.8 Flash vs Muse Wonder
    0.517 vs 0.605, Muse Wonder by 0.088
  • Gemini 3.8 Flash vs Claude Opus 5
    0.517 vs 0.598, Claude Opus 5 by 0.081
  • Gemini 3.8 Flash vs Muse Spark 1.1
    0.517 vs 0.593, Muse Spark 1.1 by 0.076
  • Gemini 3.8 Flash vs Claude Sonnet 5
    0.517 vs 0.578, Claude Sonnet 5 by 0.061
  • Gemini 3.8 Flash vs GPT-5.6 Terra
    0.517 vs 0.577, GPT-5.6 Terra by 0.060
  • Gemini 3.8 Flash vs Claude Opus 4.8 (Opus 4.8 grader)
    0.517 vs 0.574, Claude Opus 4.8 (Opus 4.8 grader) by 0.057
  • Gemini 3.8 Flash vs Grok 4.7
    0.517 vs 0.567, Grok 4.7 by 0.050
  • Gemini 3.8 Flash vs Claude Opus 4.8
    0.517 vs 0.558, Claude Opus 4.8 by 0.041
  • Gemini 3.8 Flash vs GPT-5.6 Luna
    0.517 vs 0.557, GPT-5.6 Luna by 0.040
  • Gemini 3.8 Flash vs Gemini 4 Argon
    0.517 vs 0.551, Gemini 4 Argon by 0.034
  • Gemini 3.8 Flash vs Muse Spark
    0.517 vs 0.541, Muse Spark by 0.024
  • Gemini 3.8 Flash vs GPT-5.6 Sol (August)
    0.517 vs 0.540, GPT-5.6 Sol (August) by 0.023
  • Gemini 3.8 Flash vs Kimi K3
    0.517 vs 0.532, Kimi K3 by 0.015
  • Gemini 3.8 Flash vs GLM 5.3
    0.517 vs 0.528, GLM 5.3 by 0.011
  • Gemini 3.8 Flash vs Claude Opus 4.7
    0.517 vs 0.519, Claude Opus 4.7 by 0.002
  • Gemini 3.8 Flash vs GPT-5.5
    0.517 vs 0.518, GPT-5.5 by 0.001
  • Gemini 3.8 Flash vs DeepSeek V4.1 Flash
    0.517 vs 0.507, Gemini 3.8 Flash by 0.010
  • Gemini 3.8 Flash vs Grok 4.6
    0.517 vs 0.485, Gemini 3.8 Flash by 0.032
  • Gemini 3.8 Flash vs GPT-5.4
    0.517 vs 0.481, Gemini 3.8 Flash by 0.036
  • Gemini 3.8 Flash vs GPT-5
    0.517 vs 0.462, Gemini 3.8 Flash by 0.055
  • Gemini 3.8 Flash vs GPT-5.2
    0.517 vs 0.459, Gemini 3.8 Flash by 0.058
  • Gemini 3.8 Flash vs Claude Sonnet 4.6
    0.517 vs 0.442, Gemini 3.8 Flash by 0.075
  • Gemini 3.8 Flash vs GPT-5.6 Luna (August)
    0.517 vs 0.441, Gemini 3.8 Flash by 0.076
  • Gemini 3.8 Flash vs GPT-5.1
    0.517 vs 0.396, Gemini 3.8 Flash by 0.121
  • Gemini 3.8 Flash vs GPT-5.5 Instant
    0.517 vs 0.384, Gemini 3.8 Flash by 0.133
  • Gemini 3.8 Flash vs MAI-Thinking-1
    0.517 vs 0.350, Gemini 3.8 Flash by 0.167
  • Gemini 3.8 Flash vs Claude Haiku 4.5
    0.517 vs 0.322, Gemini 3.8 Flash by 0.195

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