A benchmark for converting visual references into functional web implementations.
BenchLM is tracking Vision2Web in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.
These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.
BenchLM mirrors the published tracked score view for Vision2Web. Claude Opus 4.6 leads the public snapshot at 43.5% , followed by Kimi K2.5 (33.2%) and GLM-5V-Turbo (31.0%). BenchLM does not use these results to rank models overall.
Claude Opus 4.6
Anthropic
claude-opus-4-6
Kimi K2.5
Moonshot AI
kimi-k2-5
GLM-5V-Turbo
Z.AI
glm-5v-turbo
The published Vision2Web snapshot is tightly clustered at the top: Claude Opus 4.6 sits at 43.5%, while the third row is only 12.5 points behind. The broader top-10 spread is 12.5 points, so the benchmark still separates strong models even when the leaders cluster.
3 models have been evaluated on Vision2Web. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. Vision2Web is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Screenshot-to-web tasks
Format
Visual reference to web implementation
Difficulty
Multimodal web generation
BenchLM stores Vision2Web as a display-only screenshot-to-web benchmark reference outside the weighted core schema.
Version
Vision2Web 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A benchmark for converting visual references into functional web implementations.
Claude Opus 4.6 currently leads the published Vision2Web snapshot with a tracked score of 43.5%. BenchLM shows this benchmark for display only and does not use it in overall rankings.
3 AI models are included in BenchLM's mirrored Vision2Web snapshot, based on the public leaderboard captured on May 13, 2026.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.