Qwen3-VL-30B-A3B-Thinking qwen3-vl-30b-a3b-thinking

qwen · qwen vision reasoning efficient

#40 overall

params
30.5B (A3B)
arch
moe
context
256k
license
apache-2.0 open weights
reasoning
yes

# architecture

attn shared · reasoning GQA 32q/4kv router top-8 of 128 expert ×128 expert out ×48 layers ctx 262,144 30.5B pool · A3B/token
layers
48
d_model
2048
heads
32q / 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: #40 — score 35.9 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 24.2
bench_composite 0.30 63.1

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v163.1

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 7.5 Artificial Analysis
AA Math Index 82.3 Artificial Analysis
Ai2d 0.9 / 1 LLM Stats
AIME 2025 0.8 / 1 LLM Stats
Arena-hard-v2 0.6 / 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-d 0.9 / 1 LLM Stats
Charxiv-r 0.6 / 1 LLM Stats
Creative-writing-v3 0.8 / 1 LLM Stats
Mm-mt-bench 7.9 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Novita 128k $0.20$1.00 novita
SiliconFlowfp8 256k $0.29$1.00 openrouter 100.0%
Alibabaunknown 128k $0.20$2.40 via openrouter 100.0%

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

source aliases
aa
qwen3-vl-30b-a3b-reasoning
llmstats
qwen3-vl-30b-a3b-thinking
openrouter
qwen/qwen3-vl-30b-a3b-thinking