The Open-Source AI Stack
RSS
All models

Models · Compare

GPT-5 vs GLM-4.5

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: GPT-5 B: GLM-4.5
Released 2025-07-28
Developer OpenAIZhipu AI
Openness ProprietaryOpen
License ProprietaryMIT
OSI-approved noyes
Data released nono
Training code nono
Architecture unknownmoe
Total params 355B
Active params 32B
Experts
Context window 128K
Attention unknownunknown
Position enc. unknownunknown
Pretraining tokens 23.0T
Post-training rlhfsft, rlhf
Training hardware
$/M input $1.25
$/M output $10.00
Output tok/sec 72

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU-Pro 87.1 2026-05-21
GPQA-Diamond 85.4 2026-05-21

Code

SWE-Bench Verified 64.2 2025-07-28
LiveCodeBench 84.6 2026-05-21

Math

MATH 99.4 2026-05-21
AIME 2024 95.7 2026-05-21 91.0 2025-07-28

Context · A

OpenAI's first unified model, fusing the fast GPT-series with the deeper o-series reasoning track behind a real-time router that picks per-turn. Launched August 7 2025 via livestream; immediately default in ChatGPT, available in API and on the GitHub Models Playground. Ships in main, mini, nano, thinking, and thinking-mini variants with low/medium/high/minimal effort settings.

Context · B

Zhipu's first ARC-focused flagship (agentic, reasoning, coding), released July 28 2025 as 355B total / 32B active MoE under MIT. 23T-token pretraining run. Hybrid thinking / non-thinking modes. GLM-4.5-Air (106B / 12B) released alongside. Zhipu reports 90.6 percent tool-calling success vs Claude 4 Sonnet's 89.5 percent.

GPT-5 detail → · GLM-4.5 detail →