Z.AI: GLM 4.7
No content available for this output.
Z.AI: GLM 4.7 vs GPT-4.1
Compare Z.AI: GLM 4.7 by OpenRouter against GPT-4.1 by OpenAI, tested across 39 shared challenges. Updated February 2026.
FAQ
Loading share button...
Z.AI: GLM 4.7vsGPT-4.1
39 challenges
Why Z.AI: GLM 4.7?
Leads 1 of 1 benchmarks
Stronger on SWE-bench Verified73.8% vs 54.6%
8 months newerDec 2025
Why GPT-4.1?
No standout advantages
Favorites
Z.AI: GLM 4.7GPT-4.1
12 / 39
Estimate Complexityreasoning
Tests an AI's ability to make educated estimates based on technical knowledge
GPT-4.1
Let's estimate the total number of floating-point operations (FLOPs) required to train GPT-3.
Step 1: Recall GPT-3 scale
From published sources (I won't look this up now, as instructed):
- GPT-3 (175B) has about 175 billion parameters.
- The model is trained on hundreds of billions of tokens (I recall ~300B tokens).
Step 2: FLOPs per token per parameter
When training a transformer, roughly 2 forward passes and 1 backward pass per token (combined), and the number of FLOPs per parameter per token is about 6 (this is a number I remember from general literature).
But to be more precise, the convention is: Training one token requires about 2 FLOPs per parameter (one forward and one backward pass, with backward generally being twice as expensive as forward). Sometimes the estimate is 2, 3, 6, or even more, depending on if you count both, under what assumptions (optimizer steps, auxiliary computations, etc.), but 4 or 6 is standard.
Let's use 6 FLOPs/parameter/token (a commonly cited "rule of thumb").
Step 3: Compute FLOPs
Formula
[ \text{Total FLOPs} = \text{#params} \times \text{#tokens} \times \text{FLOPs per param per token} ]
Plug in numbers:
- #params ≈ 175 × 10⁹
- #tokens ≈ 300 × 10⁹
- FLOPs per param per token ≈ 6
[ \text{Total FLOPs} = 175 \times 10^9 \times 300 \times 10^9 \times 6 ]
Let's multiply:
- (175 \times 300 = 52,500)
- (52,500 \times 6 = 315,000)
- (10^9 \times 10^9 = 10^{18})
So,
[ \text{Total FLOPs} = 315{,}000 \times 10^{18} = 3.15 \times 10^{23} \text{ FLOPs} ]
Step 4: Order of Magnitude & Re-check
People sometimes write (3 \times 10^{23}) for GPT-3, so our estimate matches the ballpark.
Step 5: Summary Sentence
Estimate:
It would take approximately (3 \times 10^{23}) FLOPs to train GPT-3 (175B parameters, 300B tokens, 6 FLOPs/param/token).
Assumptions:
- 175B parameters
- 300B tokens
- 6 FLOPs per parameter per token
In summary:
Estimated total training compute for GPT-3: (\boxed{sim3 \times 10^{23}}) FLOPs
(based on 175B parameters, 300B tokens, 6 FLOPs/parameter/token)
Vote
2 / 39
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
Vote
3 / 39
Logic Puzzlereasoning
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
Let's break down the problem:
- Sally is a girl.
- She has 3 brothers.
- Each brother has 2 sisters.
Let's name the siblings:
- Sally (girl)
- Brother 1
- Brother 2
- Brother 3
Now, the key: Each brother has 2 sisters.
Since Sally is one of the sisters, let's see if there are more:
Suppose there is only one girl (Sally) in the family.
- Then each brother would have only 1 sister: Sally.
- But the problem says they have 2 sisters each.
Thus, Sally must have one sister (since the brothers must have 2 sisters). Let's call this other sister "Anna".
So the siblings are:
- Sally (girl)
- Anna (girl)
- Brother 1
- Brother 2
- Brother 3
Now, each brother has 2 sisters: Sally and Anna.
So, how many sisters does Sally have?
- Sally's sisters = 1 (Anna).
Final Answer:
Sally has 1 sister.
Vote
4 / 39
Math Misconception Testreasoning
Tests an AI's understanding of number representation
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
No, 9.11 is not greater than 9.9.
Here's why:
- 9.11 is actually less than 9.9.
Let's compare:
- 9.9 is equal to 9.90 (adding a zero for easier comparison).
- 9.11 < 9.90
So, 9.11 < 9.9.
Vote
5 / 39
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
Sure! Here are 5 jokes:
-
Why don't skeletons fight each other?
They don't have the guts. -
Why did the scarecrow win an award?
Because he was outstanding in his field. -
What do you call fake spaghetti?
An impasta. -
Why did the math book look sad?
Because it had too many problems. -
What do you call cheese that isn't yours?
Nacho cheese.
How many are unique?
All 5 jokes are unique; none are repeated.
Vote
6 / 39
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
Vote
7 / 39
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
Vote
8 / 39
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
No content available for this output.
Vote
9 / 39
Realistic AI Interviewconversation
Tests an AI's ability to simulate personalities and predict future trends
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
No content available for this output.
Vote
10 / 39
Satirical Fake News Headlineconversation
Tests an AI's humor and understanding of current events
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
No content available for this output.
Vote
11 / 39
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Z.AI: GLM 4.7
No content available for this output.
GPT-4.1
No content available for this output.
Vote
12 / 39
Minimalist Landing Pageweb design
Tests an AI's ability to generate a complete, working landing page
Z.AI: GLM 4.7
GPT-4.1
Vote
12 of 39