GPT-5.2-High on HealthBench Hard
On the 21-model HealthBench Hard board, GPT-5.2-High holds rank 2 with a score of 0.420. OpenAI's December 2025 model, kept on the board as a comparison row from the GPT-5.6 system card. 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 | 2 of 21 |
|---|---|
| score | 0.420 |
| source | Baichuan-M3 Technical Report (arXiv HTML 2602.06570, Section 4.2.1, paragraph preceding Figure 7 (PDF p. 23).), independent run |
| configuration | Raw/unadjusted HealthBench Hard score as evaluated by Baichuan in its M3 report; distinct from OpenAI’s length-adjusted protocol. |
| lab | OpenAI |
| context window | 400K tokens |
| API price per 1M tokens | $1.75 in / $14.00 out |
| license | proprietary |
| released | 2025-12-11 |
Where it sits
Muse Spark tops the board at 0.428, which puts GPT-5.2-High 0.008 off the lead. One place down is GPT-6 Astra at 0.366. Rows on this board are compiled from published documents, so a gap between two models is exact only when both numbers came from the same document under the same settings; the sources page shows which document each row came from.
What does GPT-5.2-High score on HealthBench Hard?
As of November 2, 2026, GPT-5.2-High scores 0.420 on HealthBench Hard, 2 of 21 models on the board. The number is read from the Baichuan-M3 Technical Report (arXiv HTML 2602.06570, Section 4.2.1, paragraph preceding Figure 7 (PDF p. 23).), independent run.
What does GPT-5.2-High cost per million tokens?
OpenAI lists GPT-5.2-High at $1.75 per million input tokens and $14.00 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-5.2-High vs Muse Spark
- GPT-5.2-High vs GPT-6 Astra
- GPT-5.2-High vs GPT-6.1 Sol
- GPT-5.2-High vs GPT-5
- GPT-5.2-High vs GPT-5.2
- GPT-5.2-High vs GPT-5.6 Sol
- GPT-5.2-High vs GPT-5.6 Terra
- GPT-5.2-High vs GPT-5.6 Luna
- GPT-5.2-High vs GPT-5.5
- GPT-5.2-High vs GPT-5.6 Sol (August)
- GPT-5.2-High vs GPT-6 Luna
- GPT-5.2-High vs GPT-6.1 Terra
- GPT-5.2-High vs GPT-6 Sol
- GPT-5.2-High vs GPT OSS 120B
- GPT-5.2-High vs GPT-5.4
- GPT-5.2-High vs GPT-5.6 Luna (August)
- GPT-5.2-High vs GPT-5.3 Chat
- GPT-5.2-High vs GPT-5.1
- GPT-5.2-High vs GPT-5.5 Instant
- GPT-5.2-High vs GPT OSS 20B
How numbers are read from their documents is on the methodology page, the document for this row is on the sources page, and how the subset was selected is on the benchmark page. The full ranking is on the leaderboard.