GLM-5.1 glm-5.1

zai-org · glm hybrid-reasoning flagship agentic

#4 overall #5 coding

params
754B
arch
moe
context
198k
license
mit open weights
released
Apr 2026
reasoning
yes
downloads/30d
101.2k

# why ranked

Overall: #4 — score 52.4 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.50 40.2
arena_elo 0.30 50.8
bench_composite 0.20 85.6

Coding: #5 — score 72.4 ● medium — one signal missing, weights renormalized

signalweightinput (0–100)
aa_coding 0.25 75.9
aider_polyglot 0.25
arena_elo_code 0.15 66.7
swe_bench_verified 0.35

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

full methodology

# trend

OGM score · last 2 days
OGM score over 2 days
overall rank (up is better)
Overall rank over 2 days

# benchmarks

benchmarkscoresourcedate
AA Coding Index 55.8 Artificial Analysis
AA Intelligence Index 40.2 Artificial Analysis
LMArena Elo 1472.0 LMArena Jul 2026
LMArena Elo (Code) 1523.0 LMArena Jul 2026
AIME 2026 1.0 / 1 LLM Stats
Browsecomp 0.8 / 1 LLM Stats
Cybergym 0.7 / 1 LLM Stats
Gdpval-aa 1281.0 / 3000 LLM Stats
Vending-bench-2 5634.4 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M blendtpsuptime
StreamLakefp8 200k $0.97$3.04$1.48 99.6%
Baidufp8 198k $0.98$3.08$1.50 99.2%
Chutesfp8 198k $0.98$3.08$1.50
GMICloudfp8 198k $0.98$3.08$1.50 99.8%
Waferfp4 198k $1.00$3.20$1.55
DeepInfrafp4 198k $1.05$3.50$1.66 99.6%
DigitalOceanunknown 64k $0.97$4.30$1.81
SiliconFlowfp8 200k $1.19$3.74$1.83 99.0%
AtlasCloudfp8 198k $1.26$3.96$1.94 90.2%
Phalaunknown 198k $1.21$4.20$1.96 88.8%
BaseTenfp4 202k $1.30$4.30$2.05 98.8%
Novitafp8 200k $1.38$4.40$2.13 95.9%
Fireworksunknown 198k $1.40$4.40$2.15
Friendliunknown 198k $1.40$4.40$2.15 99.9%
Nebiusfp8 198k $1.40$4.40$2.15 97.2%
Parasailfp8 198k $1.40$4.40$2.15 97.4%
Togetherunknown 198k $1.40$4.40$2.15 92.5%
Z.AIfp8 198k $1.40$4.40$2.15 99.9%
Venicefp8 200k $1.54$4.84$2.37 95.7%

blended = (3·input + output) / 4 per 1M tokens · cheapest first

source aliases
aa
glm-5.1
openrouter
z-ai/glm-5.1