Qwen3.5 397B A17B qwen3.5-397b-a17b

qwen · qwen hybrid-reasoning flagship

#17 overall

params
403B (A17B)
arch
moe
context
256k
license
apache-2.0 open weights
released
Feb 2026
reasoning
yes
downloads/30d
177.7k

# architecture

attn shared · reasoning GQA 32q/2kv router top-10 of 512 expert ×512 expert out ×60 layers ctx 262,144 403B pool · A17B/token
layers
60
d_model
4096
heads
32q / 2kv
head dim
256
experts
top-10 of 512
vocab
248320
family
qwen3_5_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: #17 — score 73.0 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 72.2
bench_composite 0.30 75.0

benchmark panel evidence:

complete panelscore (0–100)
aime-2026-v167.5
browsecomp-v182.6

Coding: provisional — score 66.7 ● low — a single signal; treat with caution

provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.

signalweightinput (0–100)
aa_coding 0.30 66.7
aider_polyglot 0.30
swe_bench_verified 0.40

missing signals are dropped and the remaining weights renormalized — never imputed.

full methodology

# trend

OGM score · last 55 days
OGM score over 55 days
overall rank (up is better)
Overall rank over 55 days

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

# benchmarks

benchmarkscoresourcedate
AA Coding Index 48.2 Artificial Analysis
AA Intelligence Index 26.1 Artificial Analysis
Aa-lcr 0.7 / 1 LLM Stats
AIME 2026 0.9 / 1 LLM Stats
Bfcl-v4 0.7 / 1 LLM Stats
Browsecomp 0.7 / 1 LLM Stats
Browsecomp-zh 0.7 / 1 LLM Stats
C-eval 0.9 / 1 LLM Stats
LMArena Elo (Code) 1400.0 LMArena Aug 2026
LMArena Elo (Vision) 1248.0 LMArena Aug 2026

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Featherless via hfrouter
Nebius nebius
SiliconFlow siliconflow
Vultr 256k $0.30$2.00 via modelsdev
Alibabaunknown 256k $0.39$2.34 via openrouter 99.9%
Chutesfp8 256k $0.45$3.00 chutes
DeepInfrafp8 256k $0.45$3.00 deepinfra 91.9%
Parasailfp8 256k $0.50$3.60$0.30 via openrouter 99.1%
AtlasCloudfp8 256k $0.55$3.50 atlascloud 96.9%
DigitalOceanunknown 128k $0.55$3.50$0.11 via openrouter 97.1%
Phalaunknown 256k $0.55$3.50 phala 98.8%
GMICloudfp8 256k $0.60$3.60 via openrouter 63.5%
Novitaunknown 256k $0.60$3.60 novita 98.3%
StreamLakeunknown 250k $0.60$3.60$0.12 via openrouter 97.6%
Together 256k $0.60$3.60$0.35 via modelsdev
Scaleway $0.68$4.10 via hfrouter 114
OVHcloud 256k $0.71$4.25 ovhcloud 151
Veniceunknown 125k $0.75$4.50 venice 97.3%

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
qwen3.5-397b-a17b
epoch
Qwen3.5 397B-A17B
openrouter
qwen/qwen3.5-397b-a17b