GPT-5.5 Instant on HealthBench Hard
rank 7 of 9 · updated August 16, 2026
On the 9-model HealthBench Hard board, GPT-5.5 Instant holds rank 7 with a score of 0.229. The speed-focused variant that took over as ChatGPT's default in May 2026. HealthBench Hard tests models on the 1,000 health conversations the frontier found hardest, with each response judged against its conversation's physician-written rubric and scored between 0 and 1.
Score and API facts
| rank | 7 of 9 |
|---|---|
| score | 0.229 |
| lab | OpenAI |
| context window | 400K tokens |
| API price per 1M tokens | $5.00 in / $30.00 out |
| license | proprietary |
| released | 2026-05-05 |
Where it sits
Muse Spark tops the board at 0.428, which puts GPT-5.5 Instant 0.199 off the lead. One place up is GPT-5.3 Chat at 0.259. One place down is GPT OSS 20B at 0.108. Every row on the board comes out of one run, so a gap between two models is measured on the same conversations under the same grader.
What does GPT-5.5 Instant score on HealthBench Hard?
As of August 16, 2026, GPT-5.5 Instant scores 0.229 on HealthBench Hard, 7 of 9 models on the board.
What does GPT-5.5 Instant cost per million tokens?
OpenAI lists GPT-5.5 Instant at $5.00 per million input tokens and $30.00 per million output tokens.
Head to head
The pairings that earned a full page are linked below; the rest of the differences live in the score-difference matrix.
- GPT-5.5 Instant vs Muse Spark0.229 vs 0.428 · Muse Spark by 0.199
- GPT-5.5 Instant vs GPT-5.6 Sol0.229 vs 0.331 · GPT-5.6 Sol by 0.102
- GPT-5.5 Instant vs GPT-5.6 Terra0.229 vs 0.327 · GPT-5.6 Terra by 0.098
- GPT-5.5 Instant vs GPT-5.6 Luna0.229 vs 0.320 · GPT-5.6 Luna by 0.091
- GPT-5.5 Instant vs GPT OSS 120B0.229 vs 0.300 · GPT OSS 120B by 0.071
- GPT-5.5 Instant vs GPT-5.3 Chat0.229 vs 0.259 · GPT-5.3 Chat by 0.030
- GPT-5.5 Instant vs GPT OSS 20B0.229 vs 0.108 · GPT-5.5 Instant by 0.121
- GPT-5.5 Instant vs GPT-50.229 vs 0.016 · GPT-5.5 Instant by 0.213
How the conversations are graded is on the methodology page, and how the subset was selected is on the benchmark page. The full ranking is on the leaderboard.