Qwen3-VL 235B-A22B Instruct

Qwen·Pending·Released 2025-09-23textvisionvideo
Context256k
Max output-
Input / 1M$0.4 ↗
Output / 1M$1.6 ↗
Cached in-
Benchmarks17

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

LMArena Elo#95/1411413.4 ↗
AIME25#7/1274.7% ↗
Arena-Hard v2#4/977.4% ↗
BFCL-v3#7/1067.7% ↗
HMMT25#5/1057.4% ↗
IFEval#15/2487.8% ↗
LCBV6 (25.02-25.05)54.3% ↗
MathVista (mini)#2/284.9% ↗
MMLU-Pro#26/4981.8% ↗
MMLU-Redux#6/1392.2% ↗
MMMU (val)#2/478.7% ↗
MMMU_Pro#2/468.1% ↗
ScreenSpot Pro62% ↗
SimpleQA#4/751.9% ↗
SuperGPQA#9/1760.4% ↗
VideoMME (w/o sub)#1/479.2% ↗

Qwen3-VL 235B-A22B Instruct FAQ

What is Qwen3-VL 235B-A22B Instruct?
Qwen3-VL 235B-A22B Instruct is a large language model from Qwen, released on September 23, 2025. It accepts text, image and video input.
When was Qwen3-VL 235B-A22B Instruct released?
Qwen released Qwen3-VL 235B-A22B Instruct on September 23, 2025.
How much does Qwen3-VL 235B-A22B Instruct cost?
Qwen3-VL 235B-A22B Instruct costs $0.40 per 1M input tokens and $1.60 per 1M output tokens through the Qwen API. Prices are from Qwen's official pricing as of October 5, 2026.
What is Qwen3-VL 235B-A22B Instruct's context window?
Qwen3-VL 235B-A22B Instruct has a 256K-token context window.
How does Qwen3-VL 235B-A22B Instruct score on benchmarks?
Qwen3-VL 235B-A22B Instruct has 17 cited benchmark scores, including LMArena Elo 1413.4 Elo, LMArena Vision (LMArena) 1215.1 Elo and AIME25 74.7%. Each score links to its source.

Access Qwen3-VL 235B-A22B Instruct and every other model through one endpoint with automatic failover: Respan gateway.