Alibaba Cloud / Qwen Team · apache_2_0

Qwen3 VL 235B A22B Instruct

Qwen3 VL 235B A22B Instruct by Alibaba Cloud / Qwen Team appears in 2 sources with Reasoning at 26.03. Best read for Coding, High intelligence, Low cost.

CreatorAlibaba Cloud / Qwen Team

Release date2025-09-22

Knowledge cutoffNot published

Context262K tokens

Input price$0.3/M tokens

Output price$1.5/M tokens

Modalitytext + vision

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank80ranking · source_rank

LLM Stats Code Index (estimated from arena)26.3 scoremetric

Reasoning26.03reasoning · index_reasoning

Math28.48math · index_math

Writing19.36writing · index_communication

Vision23.18multimodal · index_vision

Tool calling4.54tool_calling · index_tool_calling

Long context23.7long_context · index_long_context

Finance32.18domain · index_finance

Legal33.78domain · index_legal

Healthcare32.38domain · index_healthcare

AIME 202574.7 %math · aime_2025_score

Code Arena706.35 %coding · coding_arena_score

MMMU-Pro68.1 %multimodal · mmmu_pro_score

SimpleQA51.9 %knowledge · simpleqa_score

OSWorld66.7 %agent · osworld_score

CharXiv-R62.1 %multimodal · charxiv_r_score

ScreenSpot Pro62 %multimodal · screenspot_pro_score

Context262,144 tokenscontext · context

Speed91.53 c/sperformance · throughput

Latency850 msperformance · latency

Input price0.3 $/Mpricing · input_price

Output price1.5 $/Mpricing · output_price

Parameters236,000,000,000 paramsmodel · params

Arena Rating1,421.08metric

Arena Rank65metric

Vote Count11,523metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Qwen3 VL 235B A22B Instruct verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.