Health AI Benchmarks

GPT-6.1 Terra

2 results on 2 boards

Made by
OpenAI
Released
26 October 2026
Licence
proprietary
Context
1.05M
Input, per 1M tokens
$1
Output, per 1M tokens
$5

Health Evals Index

57.4rank 22 of 532 of 4 boards

This site's own calculation from 2 of 4 benchmarks. How it works

How this score is made
  • HealthBench Professional0.62762.7 out of 100runs −2.5 hardadjusted 65.2weight 0.446, supportingsystem cardReported by the maker.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
  • HealthBench55.155.1 out of 100runs −0.5 leveladjusted 55.6weight 0.798, coresystem cardReported by the maker.OpenAI; length-adjusted; 55.1 (51.1, 1331) (adjusted, raw, mean response characters); addendum Table 5 refers to the GPT-6 Astra card for method
  • Health Optimization Bench: incretinNo result here, and none is filled in.
  • SAFE-TeenNo result here, and none is filled in.
Adjusted average of 2 benchmarks, by weight
59.0
Field average, counts for 42.9% with 2 of 4 benchmarks
55.3
Index
= 57.4

Runs: how far that benchmark's scores sit above or below the same models' scores on the others. Adjusted: the score minus that amount. The fewer benchmarks behind a score, the more the field average counts.

Benchmark by benchmark

GPT-6.1 Terra next to the top 10 on each benchmark it has a score on, on that benchmark's own scale. Its own column is in colour.

Every result, with its source

Each against its own board only. The dot strip shows the whole board; this model is the larger red dot.

Compare GPT-6.1 Terra with other models