Qwen3.5 Omni Plus

Qwen3.5 Omni Plus

Alibaba · Released Mar 30, 2026 Professional
Intelligence #14 / 590
82.0 Our Score
Speed #209 / 279
53.4 tokens / sec
Input #363 / 592
$0.400 per 1M tokens
Output #475 / 592
$4.80 per 1M tokens
Context
— Not reported

Analysis Summary

Qwen3.5 Omni Plus is a multimodal model from Alibaba with an intelligence index of 30.6 and a GPQA score of 0.826, indicating strong scientific reasoning relative to its tier. The agentic index of 54.8 is reasonable, and the scicode score of 0.405 suggests meaningful coding capability even without a dedicated coding index. Instruction following (ifbench 0.51) and long-context reasoning (lcr 0.53) are moderate.

The omni designation implies multimodal input handling, which adds breadth for businesses needing image or document understanding alongside text. It suits content analysis, research summarisation, and structured output tasks. However, the absence of a dedicated coding index and limited tool-use data mean it is not the first choice for software engineering or agentic pipelines.

Pricing is the main constraint: $0.4/1M input is manageable, but $4.8/1M output is steep for a model at this intelligence level. It is best deployed for selective, high-value tasks rather than bulk generation workflows.

Assessed June 30, 2026

Editorial notes

Qwen3.5 Omni Plus from Alibaba reaches an intelligence index of 30.6 with strong GPQA performance and multimodal input support, but output pricing at $4.8/1M limits its cost efficiency for high-volume use.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence4.7Technical6.1Value6Content5.9
Intelligence 4.7/10
Technical 6.1/10
Content 5.9/10
Value 6/10

How Qwen3.5 Omni Plus compares

Qwen3.5 Omni Plus ranks #75 of 385 AI models we track for overall intelligence, #78 of 293 for agentic tasks. At $0.40 per million input tokens it is cheaper than 39% of comparable models.

Performance Indices

Source: Artificial Analysis

30.6 Intelligence Index
54.8 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 82.6% Graduate-level scientific reasoning
HLE 13.9% Humanity's Last Exam
SciCode 40.5% Scientific computing

Technical

TerminalBench Hard 21.2% Agentic terminal tasks
τ²-Bench 88.3% Conversational agent benchmark

Content

IFBench 51.2% Instruction following
LCR 52.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Qwen3.5 Omni Plus stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

ProviderAlibaba
Release Date March 30, 2026
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.40 $0.000400
Output $4.80 $0.004800

Leaderboard Categories

Frequently asked questions about Qwen3.5 Omni Plus

How much does Qwen3.5 Omni Plus cost?

Qwen3.5 Omni Plus costs $0.40 per million input tokens and $4.80 per million output tokens.

Who created Qwen3.5 Omni Plus?

Qwen3.5 Omni Plus is developed by Alibaba and was released on March 30, 2026.