A vision-language coding benchmark for generating correct code from visual and multimodal inputs.
As of March 2026, Claude Opus 4.6 leads the Flame-VLM-Code leaderboard with 98.8% , followed by GLM-5V-Turbo (93.8%) and Kimi K2.5 (88.8%).
Claude Opus 4.6
Anthropic
GLM-5V-Turbo
Zhipu AI
Kimi K2.5
Moonshot AI
According to BenchLM.ai, Claude Opus 4.6 leads the Flame-VLM-Code benchmark with a score of 98.8%, followed by GLM-5V-Turbo (93.8%) and Kimi K2.5 (88.8%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.
3 models have been evaluated on Flame-VLM-Code. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. Flame-VLM-Code is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Multimodal coding tasks
Format
Vision-language code generation
Difficulty
Multimodal coding
BenchLM tracks Flame-VLM-Code as a display-only multimodal coding benchmark reference.
GLM-5V-TurboVersion
Flame-VLM-Code 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 vision-language coding benchmark for generating correct code from visual and multimodal inputs.
Claude Opus 4.6 by Anthropic currently leads with a score of 98.8% on Flame-VLM-Code.
3 AI models have been evaluated on Flame-VLM-Code on BenchLM.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.