Alternatives

What are the alternatives to GLM-4.5?

GLM-4.5 ranks 87 of 94 in the overall index and costs $1 per million tokens.

Muse Ember 1.0: Ahead in the overall index (110.4 vs. 48.8) and cheaper ($0.20 vs. $1 per million tokens).

GPT OSS 120B: Level in the overall index (43.4 vs. 48.8) but cheaper: $0.20 instead of $1 per million tokens.

The alternatives by reason

Every card names the values it rests on. A model appears only once.

Stronger, not much pricier
Muse Ember 1.0
Ahead in the overall index (110.4 vs. 48.8) and cheaper ($0.20 vs. $1 per million tokens).
Overall index
110.4
Price (3:1)
$0.20
Speed
n/a
Rank 14 · Middle group
Open the profile
Similar strength, cheaper
GPT OSS 120B
Level in the overall index (43.4 vs. 48.8) but cheaper: $0.20 instead of $1 per million tokens.
Overall index
43.4
Price (3:1)
$0.20
Speed
92
Rank 93 · Lower group
Open the profile
With open weights
DeepSeek V4.1 Flash 1017
The best model with open weights, stronger: 106.7 vs. 48.8 in the overall index.
Overall index
106.7
Price (3:1)
$0.26
Speed
126
Rank 20 · Middle group
Open the profile
Similar strength, faster
Mistral Medium 3.5
Level in the overall index (46.3 vs. 48.8) and faster: 118 instead of 28 tokens per second.
Overall index
46.3
Price (3:1)
$3
Speed
118
Rank 88 · Lower group
Open the profile
The successor
GLM-4.6
The successor to GLM-4.5. Overall index 45.9 vs. 48.8.
Overall index
45.9
Price (3:1)
$0.88
Speed
28
Rank 89 · Lower group
Open the profile

The nearest generally available models by overall index, with rank, price and speed. Models with limited access and retired models are left out.

Rank	Model	Overall index	Price (3:1)	Speed
85	Claude Haiku 4.5	54.1	$2	84
86	Kimi K2 Thinking	53.2	$1.08	43
87	GLM-4.5this model	48.8	$1	28
88	Mistral Medium 3.5	46.3	$3	118
89	GLM-4.6	45.9	$0.88	28
90	Mercury 2.5	45.3	n/a	n/a
91	DeepSeek-R1	44.5	$1.15	n/a
93	GPT OSS 120B	43.4	$0.20	92

Price in dollars per million tokens, mixed from 3 parts input and 1 part output. Speed in tokens per second.