VIBE-Pro

Progress Over Time

Interactive timeline showing model performance evolution on VIBE-Pro

State-of-the-art frontier
Open
Proprietary

VIBE-Pro Leaderboard

2 models
ContextCostLicense
1205K$0.30 / $1.20
2230B1.0M$0.30 / $1.20
Notice missing or incorrect data?
About this benchmark

What is VIBE-Pro?

VIBE-Pro is an advanced version of the VIBE (Visual & Interactive Benchmark for Execution) benchmark that evaluates LLMs on professional-grade full-stack application development tasks. It measures model performance across complex real-world development scenarios including web, mobile, and backend applications with higher difficulty than the standard VIBE benchmark.

VIBE-Pro is a text benchmark evaluating models on agents and code tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.6.

Compare leaders on the best AI for agents and best AI for code leaderboards.

Current leaders

MiniMax M2.7 from MiniMax currently leads the VIBE-Pro leaderboard with a score of 0.556 across 2 evaluated AI models.

1MiniMax M2.7MiniMax55.6%
2MiniMax M2.5MiniMax54.2%

FAQ

Common questions about the VIBE-Pro benchmark and leaderboard.

What is the VIBE-Pro benchmark?

VIBE-Pro is an advanced version of the VIBE (Visual & Interactive Benchmark for Execution) benchmark that evaluates LLMs on professional-grade full-stack application development tasks. It measures model performance across complex real-world development scenarios including web, mobile, and backend applications with higher difficulty than the standard VIBE benchmark.

What is the VIBE-Pro leaderboard?

The VIBE-Pro leaderboard ranks 2 AI models based on their performance on this benchmark. Currently, MiniMax M2.7 by MiniMax leads with a score of 0.556. The average score across all models is 0.549.

What is the highest VIBE-Pro score?

The highest VIBE-Pro score is 0.556, achieved by MiniMax M2.7 from MiniMax.

How many models are evaluated on VIBE-Pro?

2 models have been evaluated on the VIBE-Pro benchmark, with 0 verified results and 2 self-reported results.

What categories does VIBE-Pro cover?

VIBE-Pro is categorized under agents and code. The benchmark evaluates text models.

What's the difference between VIBE-Pro and VIBE?

VIBE-Pro is a variant of VIBE. See the VIBE leaderboard for the broader benchmark and per-model comparison.

What is the best open-source model on VIBE-Pro?

MiniMax M2.7 by MiniMax is the top-ranked open-source model on VIBE-Pro, with a score of 0.556 (rank #1).

Which model offers the best value on VIBE-Pro?

Among models scoring within 10% of the leader, MiniMax M2.7 from MiniMax is the cheapest, at $0.30 per million input tokens with a score of 0.556.

How recent are the VIBE-Pro leaderboard results?

The VIBE-Pro leaderboard was last updated in July 2026 and currently includes 2 evaluated models.