Claude Instant 1.2vsGLM-4.6
Claude Instant 1.2 | GLM-4.6 | |
|---|---|---|
| Specifications | ||
Parameters | — | 355B |
Context window | 100k | 200k |
| 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. | — | 68% |
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. | 58.7% | — |
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. | 86.7% | — |
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. | — | 1339 |
| Overview | ||
| Company | Anthropic | Z.ai |
| Release date | Aug 9 2023 | Sep 30 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude Instant 1.2 or GLM-4.6?
Claude Instant 1.2 and GLM-4.6 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude Instant 1.2 shipped 783 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude Instant 1.2) vs 200k (GLM-4.6). Claude Instant 1.2 is proprietary, while GLM-4.6 is open weight.
Direct benchmark comparisons are unavailable — Claude Instant 1.2 and GLM-4.6 don't publish scores on any of the same benchmarks.
Frequently asked questions
Claude Instant 1.2 was released by Anthropic on Aug 9 2023.
GLM-4.6 was released by Z.ai on Sep 30 2025.
Claude Instant 1.2 has a 100k context window; GLM-4.6 has 200k.
Claude Instant 1.2 is a proprietary model released by Anthropic. GLM-4.6 is an open weight model released by Z.ai.