Claude 2vsGLM-4.7
Claude 2 | GLM-4.7 | |
|---|---|---|
| Specifications | ||
Context window | 100k | 128k |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 73.8% |
Function synthesis HumanEval164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 71.2% | — |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 41% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 52% |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 24.8% |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 42.8% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 85.7% |
General knowledge MMLUA 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 78.5% | — |
Grade-school math GSM8KGrade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 88% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1433 |
| Overview | ||
| Company | Anthropic | Z.ai |
| Release date | Jul 11 2023 | Dec 22 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude 2 or GLM-4.7?
Claude 2 and GLM-4.7 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 2 shipped 895 days before GLM-4.7, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude 2) vs 128k (GLM-4.7). Claude 2 is proprietary, while GLM-4.7 is open weight.
Direct benchmark comparisons are unavailable — Claude 2 and GLM-4.7 don't publish scores on any of the same benchmarks.
Frequently asked questions
Claude 2 was released by Anthropic on Jul 11 2023.
GLM-4.7 was released by Z.ai on Dec 22 2025.
Claude 2 has a 100k context window; GLM-4.7 has 128k.
Claude 2 is a proprietary model released by Anthropic. GLM-4.7 is an open weight model released by Z.ai.