Qwen3-VL-235B-A22B-Instruct qwen3-vl-235b-a22b-instruct

qwen · qwen vision flagship

#45 overall

params
235.7B (A22B)
arch
moe
context
256k
license
apache-2.0 open weights

# architecture

attn shared GQA 64q/4kv router top-8 of 128 expert ×128 expert out ×94 layers ctx 262,144 235.7B pool · A22B/token
layers
94
d_model
4096
heads
64q / 4kv
head dim
128
experts
top-8 of 128
vocab
151936
family
qwen3_vl_moe_text

signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.

# why ranked

Overall: #45 — score 31.6 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 28.9
bench_composite 0.30 38.1

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v138.1

full methodology

# trend

OGM score · last 54 days
OGM score over 54 days
overall rank (up is better)
Overall rank over 54 days

methodology changed during this history window; score movement across that boundary is not model movement. See methodology v5.

# benchmarks

benchmarkscoresourcedate
AA Intelligence Index 8.4 Artificial Analysis
AA Math Index 70.7 Artificial Analysis
Ai2d 0.9 / 1 LLM Stats
AIME 2025 0.7 / 1 LLM Stats
Androidworld-sr 0.6 / 1 LLM Stats
Arena-hard-v2 0.8 / 1 LLM Stats
Bfcl-v3 0.7 / 1 LLM Stats
Blink 0.7 / 1 LLM Stats
Cc-ocr 0.8 / 1 LLM Stats
Charadessta 0.6 / 1 LLM Stats
Charxiv-r 0.6 / 1 LLM Stats
Creative-writing-v3 0.9 / 1 LLM Stats
Csimpleqa 0.8 / 1 LLM Stats
Docvqatest 1.0 / 1 LLM Stats
Mm-mt-bench 8.5 LLM Stats
Screenspot 1.0 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
DeepInfrafp8 256k $0.20$0.88 deepinfra 96.4%
Alibabaunknown 128k $0.26$1.04 via openrouter 99.6%
Amazon Bedrock $0.26$1.33 bedrock
Novitabf16 128k $0.30$1.50 novita 95.9%
SiliconFlow 262k $0.30$1.50 via modelsdev
Parasailfp8 128k $0.21$1.90$0.10 via openrouter 98.7%
Venicefp8 125k $0.21$1.90 venice 97.2%
Qwen Ai Platform 128k $0.40$1.60 via litellm
Qwencloud 128k $0.40$1.60 via litellm

sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price

# variants

Qwen3-VL-235B-A22B-Thinking

source aliases
aa
qwen3-vl-235b-a22b-instruct
bedrock
Qwen3 VL 235B A22B
llmstats
qwen3-vl-235b-a22b-instruct
openrouter
qwen/qwen3-vl-235b-a22b-instruct