Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 6B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 8k |
| Benchmarks | ||
HumanEvalFunction synthesis — 164 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. | 86.6% | 58.5% |
MATHReasoning — accuracy on the original competition mathematics test set | 81.1% | 25.7% |
GSM8KGrade-school math — Grade-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. | 93.8% | 72.3% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 37.8% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 76.3% | — |
HellaSwagReasoning — commonsense completion of short scenarios | — | 79.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 64.5% | — |
MMLUGeneral knowledge — A 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. | — | 61.4% |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Nov 15 2024 | Oct 27 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen2.5-Turbo (1M)vsClaude Fable 5.2ChatGLM3-6BvsClaude Fable 5.2Qwen2.5-Turbo (1M)vsGPT-6.2 AstraChatGLM3-6BvsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGemini 4 NeonChatGLM3-6BvsGemini 4 NeonQwen2.5-Turbo (1M)vsMuse EmberChatGLM3-6BvsMuse EmberQwen2.5-Turbo (1M)vsGrok 4.7ChatGLM3-6BvsGrok 4.7Qwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017ChatGLM3-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen2.5-Turbo (1M) leads ChatGLM3-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). ChatGLM3-6B shipped 385 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Qwen2.5-Turbo (1M)) vs 8k (ChatGLM3-6B). Qwen2.5-Turbo (1M) is closed, while ChatGLM3-6B is open weight.
On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs ChatGLM3-6B at 58.5%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs ChatGLM3-6B at 25.7%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs ChatGLM3-6B at 72.3%.