Qwen3 235B A22B Instruct 2507 qwen3-235b-a22b-instruct-2507

qwen · qwen flagship

#39 overall

params
235.1B (A22B)
arch
moe
context
256k
license
apache-2.0 open weights
released
Jul 2025
train compute
4.8e+24 FLOP
downloads/30d
116.1k

# architecture

attn shared GQA 64q/4kv router top-8 of 128 expert ×128 expert out ×94 layers ctx 262,144 235.1B pool · A22B/token
layers
94
d_model
4096
heads
64q / 4kv
head dim
128
experts
top-8 of 128
vocab
151936
family
qwen3_moe

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: #39 — score 37.8 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 44.3
bench_composite 0.30 22.5

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v122.5

Coding: provisional — score 22.8 ● 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 22.8
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 51 days
OGM score over 51 days
overall rank (up is better)
Overall rank over 51 days

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

# benchmarks

benchmarkscoresourcedate
AA Coding Index 22.1 Artificial Analysis
AA Intelligence Index 13.1 Artificial Analysis
AA Math Index 91.0 Artificial Analysis
Aider-polyglot 0.6 / 1 LLM Stats
AIME 2025 0.7 / 1 LLM Stats
Arc-agi 0.4 / 1 LLM Stats
Arena-hard-v2 0.8 / 1 LLM Stats
Bfcl-v3 0.7 / 1 LLM Stats
Creative-writing-v3 0.9 / 1 LLM Stats
Csimpleqa 0.8 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
GMICloudfp8 256k $0.09$0.35$0.02 via openrouter 99.3%
DeepInfrafp8 256k $0.09$0.55 deepinfra 98.1%
Novitafp8 128k $0.09$0.58 novita 98.7%
Alibabaunknown 128k $0.15$0.60 via openrouter 100.0%
Venicefp8 125k $0.15$0.75 venice 97.9%
Nebiusfp8 256k $0.20$0.60 openrouter 53.9%
Nscale 32k $0.20$0.60 via hfrouter 9
Parasailfp8 128k $0.14$0.80$0.05 via openrouter 99.9%
StreamLakeunknown 125k $0.21$0.84 via openrouter 99.5%
AtlasCloudfp8 128k $0.20$0.88 atlascloud 99.4%
Amazon Bedrock $0.22$0.88 bedrock
Googleunknown 256k $0.22$0.88 via openrouter 100.0%
Googleunknown 256k $0.25$1.00 via openrouter 99.9%
Replicate $0.26$1.06 via litellm
Scaleway $0.85$2.56 via hfrouter 95
Crusoe 256k $3.00$3.00 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

source aliases
aa
qwen3-235b-a22b-instruct-2507
bedrock
Qwen3 235B A22B 2507
epoch
Qwen3-235B-A22B (Jul 2025)
llmstats
qwen3-235b-a22b-instruct-2507
openrouter
qwen/qwen3-235b-a22b-2507