OpenAIMIT HAN LabImage model matchup
GPT Image 1.5vs.HART-0.7B-1024px
Which one is better?
HART-0.7B-1024px has no test of our own, no arena rating and no API price yet.
GPT Image 1.5
Rank 31 of 108
HART-0.7B-1024px
not tested yet
GPT Image 1.5
Rank 13 of 21
HART-0.7B-1024px
not in the arena
GPT Image 1.5
HART-0.7B-1024px
Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench Image v2 run; prices compared with 28 models with an API price.
Test images from GraduallyBench Image v2
Same task, the first image of each.
No image from the four fixed tasks for HART-0.7B-1024px yet.
Result for “Typography and layout”:only GPT Image 1.5 tested
What the rating looks at: Legible text, hierarchy, and composition.
“Ahead”: the 95 % ranges of both values do not overlap. “Slightly ahead”: a higher value, but the ranges overlap.
Missing image run for HART-0.7B-1024px
The reviewed vendor runner requires CUDA and custom CUDA kernels. No suitable MPS runtime has been verified for this Mac. The vendor-linked demo was unreachable on November 3, 2026 (HTTP 530), so no hosted test could be submitted there. Check the official demo once restored or a supported CUDA runtime for the exact model version.
DocumentationSubscription and API
GPT Image 1.5
- Subscription
- No OpenAI subscription includes this model. Through other providers from $6 a month (ElevenLabs Starter, with limited credits). 42 plans in Germany.
- Via API
- $0.13 per image, 100 images $13.30.
- Weights
- Closed weights.
HART-0.7B-1024px
- Subscription
- n/a No plan in Germany names exactly this model.
- Via API
- No API price known (access: local).
- Weights
- Open weights.
Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.
Arena rating (LMArena) from Nov 10, 2026 · GraduallyBench Image v2 from Nov 7, 2026 · API prices from Nov 10, 2026 · Subscription database from Sep 29, 2026 (43 days old)
All data side by side
The better value is bold. For ratings only when the gap is clear.
| Kennzahl | GPT Image 1.5 | HART-0.7B-1024px |
|---|---|---|
| Ratings | ||
| Arena ratingfrom votes by users, higher is better | 1,236 | n/a |
| Arena rank | Rank 13 of 21 | n/a |
| Arena votesmore votes, a safer rating | 169,495 | n/a |
| GraduallyBench Image v2our own benchmark, 0 to 100 | 71 | n/a |
| GraduallyBench Image v2 by task | ||
| Typography and layoutLegible text, hierarchy, and composition | 68 | n/a |
| Product photographyMaterials, reflections, and fine details | 58 | n/a |
| Character and detailAnatomy, clothing, and spatial consistency | 91 | n/a |
| InfographicNumbers, labels, and visual organization | 66 | n/a |
| API price | ||
| Per imagelower is better | $0.13 | n/a |
| 100 images | $13.30 | n/a |
| Profile | ||
| Released | December 2025 | October 2024 |
| Weightsopen means: runs locally | proprietary | open |
| Lifecycle | Marked as deprecated by OpenAI; removed from the API on December 1, 2026 | no notice |
| Access | API, Web app | local |
| Parameters | not published | 0.7 billion |
| Largest output | 1,536 × 1,024 pixels | 1,024 × 1,024 pixels |
| Plans in Germanynaming exactly this model | 42 | n/a |
API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.
Sources: GPT Image 1.5 model source, status source (verified Aug 15, 2026) · HART-0.7B-1024px model source (verified Nov 1, 2026)
Arena ratings by category
From blind votes on Artificial Analysis and LMArena; the sources are named under the card. “Ahead” means the lead is clear.
No shared arena score in the stored snapshot
The stored benchmark database contains no measurement for GPT Image 1.5 and HART-0.7B-1024px from the same arena and category. Older model versions are not used as substitutes.
More comparisons
Compare GPT Image 1.5 and HART-0.7B-1024px with the models people compare them with most often.