GLM-4.7 Flash glm-4.7-flash

zai-org · glm efficient

#28 overall

params
31.2B
arch
dense
context
198k
license
mit open weights
released
Jan 2026
reasoning
yes
downloads/30d
1.9M

# architecture

attn shared · reasoning MHA ×20 feed-forward (dense) every parameter, every token out ×47 layers ctx 202,752 31.2B — no routing
layers
47
d_model
2048
heads
20q / 20kv
head dim
102
experts
top-4 of 64 + 1 shared
vocab
154880
family
glm4_moe_lite

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: #28 — score 57.5 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 55.7
bench_composite 0.30 61.9

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v178.7
browsecomp-v145.1

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 Intelligence Index 16.6 Artificial Analysis
AIME 2025 0.9 / 1 LLM Stats
Browsecomp 0.4 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Featherless via hfrouter
DeepInfrabf16 198k $0.06$0.40$0.01 via openrouter 99.8%
Venicefp8 125k $0.06$0.40 venice 99.6%
Cloudflareunknown 128k $0.06$0.40 via openrouter 98.4%
Amazon Bedrock $0.07$0.40 bedrock
Novitabf16 200k $0.07$0.40 novita 74.2%

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
glm-4.7-flash
openrouter
z-ai/glm-4.7-flash