Qwen3.5 122B A10B qwen3.5-122b-a10b

qwen · qwen hybrid-reasoning

#18 overall

params
125B (A10B)
arch
moe
context
256k
license
apache-2.0 open weights
released
Feb 2026
reasoning
yes
downloads/30d
698.3k

# architecture

attn shared · reasoning GQA 32q/2kv router top-8 of 256 expert ×256 expert out ×48 layers ctx 262,144 125B pool · A10B/token
layers
48
d_model
3072
heads
32q / 2kv
head dim
256
experts
top-8 of 256
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: #18 — score 70.4 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 67.0
bench_composite 0.30 78.4

benchmark panel evidence:

complete panelscore (0–100)
browsecomp-v178.4

Coding: provisional — score 61.4 ● 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 61.4
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 45.7 Artificial Analysis
AA Intelligence Index 24.8 Artificial Analysis
Aa-lcr 0.7 / 1 LLM Stats
Ai2d 0.9 / 1 LLM Stats
Androidworld-sr 0.7 / 1 LLM Stats
Babyvision 0.4 / 1 LLM Stats
Bfcl-v4 0.7 / 1 LLM Stats
Browsecomp 0.6 / 1 LLM Stats
Browsecomp-zh 0.7 / 1 LLM Stats
C-eval 0.9 / 1 LLM Stats
Cc-ocr 0.8 / 1 LLM Stats
Charxiv-r 0.8 / 1 LLM Stats
Codeforces 0.9 / 3000 LLM Stats
Countbench 1.0 LLM Stats
Vlmsareblind 1.0 / 1 LLM Stats
LMArena Elo (Code) 1358.0 LMArena Aug 2026

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Libertai 256k $0.25$1.75 via litellm
Alibabaunknown 256k $0.26$2.08 via openrouter 95.1%
SiliconFlowfp8 256k $0.26$2.08 openrouter 99.3%
DeepInfrafp4 256k $0.29$2.40 deepinfra 95.9%
AtlasCloudfp8 256k $0.30$2.40 atlascloud 99.3%
Novitabf16 256k $0.40$3.20 novita 99.0%

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
qwen3.5-122b-a10b
epoch
Qwen3.5-122B-A10B
hf
nvidia/Qwen3.5-122B-A10B-NVFP4
openrouter
qwen/qwen3.5-122b-a10b