0

GLM 4.7 vs GPT-5

Head to head on 17 shared benchmarks, with price, context window, and release dates.

Benchmark scores

75

evals · sort by any column, ⤢ to expand fullscreen

Model
GPT-5

OpenAI

48.3%61.1%1623elo72.832.4%68.6%6.6%45.0%54.3%49.6%83.7%82.0%18.0%37.8%73.4%12.9%0.0%46.7%91.1%88.0%94.6%0.0%0.150.0%68.1%4.5857.7%-80.0%80.0%-91.7%0.0%88.9%83.3%-100.0%48.9%83.4%58.2%-------37.5%-0.521.62100.0%86.1%0.0%92.7%92.7%-93.3%10.0%0.0%65.5%60.0%0.26-0.0%43.7%74.9%74.4%2.3487.5%0.8620.1%54.8%90.0%90.0%56.7%
GLM 4.7

Zai

48.0%46.4%1411elo662.4%66.4%6.4%54.6%56.2%32.8%68.6%79.4%6.0%35.4%68.8%30.3%94.2%----------46.7%--28.6%----90.0%----60.8%73.1%55.2%35.7%65.2%76.0%59.7%-33.3%-------33.3%------100.0%-----------51.9%
2 / 2 models
AttributeGLM 4.7

Zai

GPT-5

OpenAI

DescriptionGLM-4.7 is an AI model from Zai, released with open weights.OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant.
FamilyGlmGPT 5
Params-Undisclosed (closed)
Open weightsopenclosed
LicensemitProprietary
Released22 Dec 20257 Aug 2025
Context204,800400,000
Input $/1M$0.60-
Output $/1M$2.20-
Cache read $/1M$0.080$0.125
Cache write $/1M--
Speed0 tok/s0 tok/s
Latency0.00 s0.00 s
Modalitiestexttext, image, file
Providers-openai
PublisherZaiOpenAI
Reported scores

FAQ

Is GLM 4.7 or GPT-5 better?
Across the 17 benchmarks both models report on Sophon, GPT-5 leads on 13 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
How do GLM 4.7 and GPT-5 compare on GPQA Diamond?
GLM 4.7 scores 66.4% and GPT-5 scores 68.6% on GPQA Diamond.
When were GLM 4.7 and GPT-5 released?
GLM 4.7 was released 22 Dec 2025 by Zai. GPT-5 was released 7 Aug 2025 by OpenAI.

Comparing something else? Build your own side-by-side.