modelbenchmark.io

GLM-5

Alibaba · glm-5

Compare

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Specification

alibaba-cn listing

Context
203K
Max output
16K
Released
2026-02-11
Knowledge cutoff
2025-04
Retires
2026-10-16
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · alibaba-cn list price

Input
$0.573
Output
$2.58
Cache read
$0.20
Cache write
free

Quality

5 benchmarks · 2 sources

Composite
68th
percentile of 344 scored models
Rank
110 / 344
±0.06 sd
Evidence
5 × 2
3 or more benchmarks, from 2 or more sources
Effort range
0.7
points between effort settings
coding74th1/3 bench
reasoning91st1/4 bench
math49th3/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
GPQA diamond87.8 ±2.3defaultEpoch AI2026-02-12
SWE-Bench verified72.8high · mini-SWE-agentSWE-bench—
↳72.1 ±2.1defaultEpoch AI2026-02-15
Sources and settings disagree by 0.7 points. Both figures stand.
OTIS Mock AIME 2024-202580.0 ±6.0defaultEpoch AI2026-02-12
FrontierMath-Tier-4-2025-07-011.1 ±2.1default · 2 runsEpoch AI2026-02-19
FrontierMath-v19.3 ±2.2default · 2 runsEpoch AI2026-02-19

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 48 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibaba-cnvendor$0.573$2.58——203K16K—
alibaba-coding-planfreefreefreefree203K16K—
alibaba-coding-plan-cnfreefreefreefree203K16K—
alibaba-token-planfreefreefreefree203K16K—
alibaba-token-plan-cnfreefreefreefree203K16K—
scnet-token-planfreefreefree—205K131K—
tencent-coding-planfreefreefreefree203K16K—
llmgateway$0.573$2.58$0.144free203K131K—
llmgateway-providers
$0.573
$1.00
$2.58
$3.20
$0.20—
203K
203K
16K
131K
—
qiniu-ai · z-ai$0.5797$2.6087——200K128K—
zenmux · z-ai$0.58$2.60$0.14—200K128K—
zhipuai$0.5976$2.6891$0.1494free205K131K—
302ai$0.60$2.60——205K131K—
crossmodel · z-ai$0.60$3.00$0.16$0.60200K128K—
deepinfra$0.60$2.08$0.12—203K203K—
deepinfra · zai-org$0.60$2.08$0.12—203K16K—
fastrouter · z-ai$0.60$2.08$0.12—205K131K—
nano-gpt · thinking$0.60$1.90$0.10—200K128K—
nano-gpt · z-ai$0.60$1.90$0.10—200K128K—
dinference$0.75$2.40——200K128K—
meganova · zai-org$0.80$2.56$0.20—203K131K—
tokengo · z-ai$0.89$3.2647$0.2226—205K131K—
baseten$0.95$3.15————2026-10-16
siliconflow · zai-org$0.95$2.55$0.20—205K131K—
abacus · zai-org$1.00$3.20——205K131K—
edenai · zai$1.00$3.20$0.20—203K131K—
huggingface · zai-org$1.00$3.20$0.20—203K131K—
impossibl · zai$1.00$3.20$0.20—205K131K—
kilo · z-ai$1.00$3.20$0.20—203K131K—
llmgateway-providers · tencent$1.00$3.20$0.20—200K128K—
llmgateway-providers · zai$1.00$3.20$0.20—203K131K—
merge-gateway · zai$1.00$3.20$0.20free200K131K—
novita$1.00$3.20$0.20—203K131K—
novita-ai · zai-org$1.00$3.20$0.20—203K131K—
ofox · z-ai$1.00$3.20$0.20—205K131K—
opencode$1.00$3.20$0.20—205K131K—
openrouter · z-ai$1.00$3.20$0.20—205K131K—
orcarouter · z-ai$1.00$3.20$0.26free205K131K—
poe$1.00$3.20$0.20—205K131K—
siliconflow-cn · pro$1.00$3.20——205K205K—
streamlake · streamlake$1.00$3.20$0.20—203K128K—
tempr · zai$1.00$3.20$0.20free205K131K—
tensorx · z-ai$1.00$3.20$0.25$1.25203K203K—
together_ai$1.00$3.20——203K203K2026-06-22
togetherai · zai-org$1.00$3.20——203K131K—
vercel · zai$1.00$3.20——203K131K—
zai$1.00$3.20$0.20free205K131K—
zai · zai$1.00$3.20$0.20free200K128K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02kilo · z-aiCache read$0.12
2026-10-15kilo · z-aiCache read$0.20
2026-10-20kilo · z-aiCache read$0.12
2026-10-21kilo · z-aiCache read$0.20
2026-09-02nano-gpt · thinkingCache read$0.13
2026-10-13nano-gpt · thinkingCache read$0.10
2026-09-02nano-gpt · z-aiCache read$0.13
2026-10-13nano-gpt · z-aiCache read$0.10
2026-09-02openrouter · z-aiCache read$0.12
2026-10-15openrouter · z-aiCache read$0.20
2026-10-20openrouter · z-aiCache read$0.12
2026-10-21openrouter · z-aiCache read$0.20
2026-09-02zhipuaiCache read$0.20
2026-10-20zhipuaiCache read$0.1494
2026-09-02hyperCache write$0.455
2026-09-02hyperCache write$0.425
2026-09-04hyperCache write$0.465
2026-09-05hyperCache write$0.43
2026-09-02fastrouter · z-aiInput$0.95
2026-10-22fastrouter · z-aiInput$0.60
2026-09-02hyperInput$0.91
2026-09-02hyperInput$0.85
2026-09-04hyperInput$0.93
2026-09-05hyperInput$0.86
2026-09-15hyperInput$0.94
2026-09-16hyperInput$0.86
2026-09-02kilo · z-aiInput$0.60
2026-10-15kilo · z-aiInput$1.00
2026-10-20kilo · z-aiInput$0.60
2026-10-21kilo · z-aiInput$1.00
2026-09-02llmgatewayInput$0.72
2026-10-22llmgatewayInput$0.573
2026-09-02llmgateway-providersInput$1.00
2026-09-04llmgateway-providersInput$0.573
2026-09-24llmgateway-providersInput$1.00
2026-10-19llmgateway-providersInput$0.573
2026-10-20llmgateway-providersInput$1.00
2026-10-21llmgateway-providersInput$0.573
2026-10-24llmgateway-providersInput$1.00
2026-10-26llmgateway-providersInput$0.573
2026-10-27llmgateway-providersInput$1.00
2026-10-28llmgateway-providersInput$0.573
2026-10-29llmgateway-providersInput$1.00
2026-10-31llmgateway-providersInput$0.573
2026-09-02nano-gpt · thinkingInput$0.50
2026-10-13nano-gpt · thinkingInput$0.60
2026-09-02nano-gpt · z-aiInput$0.50
2026-10-13nano-gpt · z-aiInput$0.60
2026-09-02openrouterInput$0.80
2026-09-06openrouterInput$0.60
2026-09-02openrouter · z-aiInput$0.60
2026-10-15openrouter · z-aiInput$1.00
2026-10-20openrouter · z-aiInput$0.60
2026-10-21openrouter · z-aiInput$1.00
2026-09-02zhipuaiInput$1.00
2026-10-20zhipuaiInput$0.5976
2026-09-02fastrouter · z-aiOutput$3.15
2026-10-22fastrouter · z-aiOutput$2.08
2026-09-02hyperOutput$2.934
2026-09-02hyperOutput$2.774
2026-09-04hyperOutput$2.878
2026-09-05hyperOutput$2.784
2026-09-12hyperOutput$2.752
2026-09-15hyperOutput$3.008
2026-09-16hyperOutput$2.752
2026-09-02kilo · z-aiOutput$1.92
2026-10-15kilo · z-aiOutput$3.20
2026-10-20kilo · z-aiOutput$1.92
2026-10-21kilo · z-aiOutput$3.20
2026-09-02llmgatewayOutput$2.30
2026-10-22llmgatewayOutput$2.58
2026-09-02llmgateway-providersOutput$3.20
2026-09-04llmgateway-providersOutput$2.58
2026-09-24llmgateway-providersOutput$3.20
2026-10-19llmgateway-providersOutput$2.58
2026-10-20llmgateway-providersOutput$3.20
2026-10-21llmgateway-providersOutput$2.58
2026-10-24llmgateway-providersOutput$3.20
2026-10-26llmgateway-providersOutput$2.58
2026-10-27llmgateway-providersOutput$3.20
2026-10-28llmgateway-providersOutput$2.58
2026-10-29llmgateway-providersOutput$3.20
2026-10-31llmgateway-providersOutput$2.58
2026-09-02nano-gpt · thinkingOutput$2.55
2026-10-13nano-gpt · thinkingOutput$1.90
2026-09-02nano-gpt · z-aiOutput$2.55
2026-10-13nano-gpt · z-aiOutput$1.90
2026-09-02openrouterOutput$2.56
2026-09-06openrouterOutput$1.92
2026-09-02openrouter · z-aiOutput$1.92
2026-10-15openrouter · z-aiOutput$3.20
2026-10-20openrouter · z-aiOutput$1.92
2026-10-21openrouter · z-aiOutput$3.20
2026-09-02zhipuaiOutput$3.20
2026-10-20zhipuaiOutput$2.6891
2026-09-11hyperCache read$0.43
2026-09-15hyperCache read$0.47
2026-09-16hyperCache read$0.43
2026-09-13together_aiInput$1.00
2026-09-24together_aiInput$1.00
2026-09-13together_aiOutput$3.20
2026-09-24together_aiOutput$3.20

Other listings of this model

same model, different key

More from Alibaba

most-hosted first