GPT-5 High vs GPT-5 Medium: Specs & Benchmark Comparison
GPT-5 High and GPT-5 Medium both come from OpenAI, and both were released in August 2025.
The two models share 2 published benchmarks. They split them evenly, 1 to 1. The widest gaps are on AIME 2025, where GPT-5 High scores 95.0% against 89.0%; GPQA, where GPT-5 Medium scores 88.0% against 87.0%. Averaged across everything we track, GPT-5 High sits at 91.0% and GPT-5 Medium at 88.5%.
On price the two are close: GPT-5 High costs $1.25 per million input tokens and $10 per million output tokens, GPT-5 Medium $1.25 and $10. Both accept a context window of about 400K tokens. Both accept text and images as input.
| Characteristic | GPT-5 High | GPT-5 Medium |
|---|---|---|
| Company | OpenAI | OpenAI |
| Release Date | August 6, 2025 | August 6, 2025 |
| Parameters | — | — |
| Multimodal | Yes | Yes |
| Context (input) | 400K | 400K |
| Context (output) | 128K | 128K |
| Input Price / 1M | $1.25 | $1.25 |
| Output Price / 1M | $10.00 | $10.00 |
| Average Score | 91.0% | 88.5% |
| Benchmarks | ||
| AIME 2025 | 95.0% | 89.0% |
| GPQA | 87.0% | 88.0% |
Visual Benchmark Comparison
Verdict
Both models show equal results — the choice depends on your specific use case.
Both models show comparable average scores: GPT-5 High — 0.9, GPT-5 Medium — 0.9.
API cost is identical: input $1.25/1M, output $10.00/1M tokens.
Same context size: 400K tokens.
Both models were released around the same time: 8/6/2025 and 8/6/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — GPT-5 High or GPT-5 Medium?
Which model is cheaper — GPT-5 High or GPT-5 Medium?
Which has a larger context window — GPT-5 High or GPT-5 Medium?
The GPT-5 High and GPT-5 Medium comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GPT-5 High or GPT-5 Medium page. See also the complete list of AI model comparisons.