# VIBE V2

> A display-only MiniMax provider benchmark for end-to-end coding-agent and product-building tasks.

Canonical page: https://benchlm.ai/benchmarks/vibev2

- Category: [Coding](/coding)
- Last updated: September 27, 2026

## About VIBE V2

- Year: 2026
- Tasks: End-to-end coding-agent tasks
- Format: Task success rate
- Difficulty: Frontier coding-agent workflows
- Paper: [MiniMax M3 model card](https://huggingface.co/MiniMaxAI/MiniMax-M3)

MiniMax reports VIBE V2 in the M3 comparison chart. BenchLM tracks it as a display-only provider row because it is not part of the weighted coding schema.

VIBE V2 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [MiniMax M3](/models/minimax-m3) | MiniMax | 50.1% |

## FAQ

### What does VIBE V2 measure?

A display-only MiniMax provider benchmark for end-to-end coding-agent and product-building tasks.

### Which model scores highest on VIBE V2?

MiniMax M3 by MiniMax currently leads with a score of 50.1% on VIBE V2.

### How many models are evaluated on VIBE V2?

1 AI models have been evaluated on VIBE V2 on BenchLM.

### Does VIBE V2 affect BenchLM's overall score?

Not directly. VIBE V2 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.