Skip to main content
BenchLM

VITA-Bench

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

An interactive real-world agent benchmark grounded in practical consumer-service tasks such as delivery, in-store consumption, and online travel workflows.

Benchmark score on VITA-Bench — September 27, 2026

We compile the VITA-Bench rows from benchmark-owner or independent runs and provider self-reports. Qwen3.7 Max leads the table at 47.9%, followed by Qwen3.7 Plus (45.6%) and Qwen3.6 Plus (44.3%). We do not use these results to rank models overall.

12 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (12 models)

Score
1
Qwen3.7 MaxAlibaba · Closed
47.9%
2
Qwen3.7 PlusAlibaba · Closed
45.6%
3
Qwen3.6 PlusAlibaba · Closed
44.3%
4
Qwen3.5 397BAlibaba · Open weight
43.7%
5
Agents-A1-4BInternScience · Open weight
40.3%
6
Agents-A1InternScience · Open weight
38.8%
7
Qwen3.6-35B-A3BAlibaba · Open weight
35.6%
8
Claude Opus 4.5Anthropic · Closed
23.3%
9
LongCat-Flash-Lite-SparseMeituan · Open weight
21.7%
10
DeepSeek V3.2DeepSeek · Open weight
18.5%
11
Claude Sonnet 4.5Anthropic · Closed
17.0%
12
GLM-4.7Z.AI · Open weight
15.5%

Among the reported VITA-Bench rows, Qwen3.7 Max is first at 47.9%. The third row is 3.6 points behind. The broader top-10 range is 29.4 points, so the table still separates the published systems.

12 models have been evaluated on VITA-Bench. The benchmark falls in the Agentic category. VITA-Bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About VITA-Bench

Year

2025

Tasks

Interactive consumer-service agent tasks

Format

End-to-end interactive agent evaluation

Difficulty

Long-horizon real-world workflows

VITA-Bench is built to test realistic interactive agent behavior rather than toy tool calls. It stresses long-horizon coordination, tool selection, changing user intent, and domain switching across daily-life applications.

Freshness and provenance

Version

VITA-Bench 2025

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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.

Questions

What does VITA-Bench measure?

An interactive real-world agent benchmark grounded in practical consumer-service tasks such as delivery, in-store consumption, and online travel workflows.

Which model scores highest on VITA-Bench?

Qwen3.7 Max by Alibaba currently leads with a score of 47.9% on VITA-Bench.

How many models are evaluated on VITA-Bench?

12 AI models have been evaluated on VITA-Bench on BenchLM.

Last updated: September 27, 2026 · BenchLM version VITA-Bench 2025

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.