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. | 7B/14B | 9B/32B |
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 | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.1032B checkpoint |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $0.10 |
| — | $25.00Z.ai list price | |
| Benchmarks | ||
IFEvalAgentic tasks — following verifiable instructions in generated responses | 84.3% | 87.6% |
SWE-Bench VerifiedCoding — Real 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. | — | 27.2% |
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. | 38.6% | — |
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. | 88.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 79.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 63.3% | — |
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. | 94.8% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Jan 27 2025 | Apr 14 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen2.5-1MvsClaude Fable 5.2GLM-4-0414vsClaude Fable 5.2Qwen2.5-1MvsGPT-6.2 AstraGLM-4-0414vsGPT-6.2 AstraQwen2.5-1MvsGemini 4 NeonGLM-4-0414vsGemini 4 NeonQwen2.5-1MvsMuse EmberGLM-4-0414vsMuse EmberQwen2.5-1MvsGrok 4.7GLM-4-0414vsGrok 4.7Qwen2.5-1MvsDeepSeek-V4.1-Flash-1017GLM-4-0414vsDeepSeek-V4.1-Flash-1017Frequently asked questions
GLM-4-0414 leads Qwen2.5-1M on 1 of the 1 benchmark they both report (IFEval). Only GLM-4-0414 has a verified first-party price for an available API: $0.10 per million input tokens and $0.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen2.5-1M. The listed GLM-4-0414 rates use the “32B checkpoint” pricing scope. Qwen2.5-1M shipped 77 days before GLM-4-0414, so benchmark comparisons should account for the intervening progress.
Qwen2.5-1M has 7B/14B parameters, while GLM-4-0414 has 9B/32B. Context windows are 1M (Qwen2.5-1M) vs 128k (GLM-4-0414).
On IFEval, GLM-4-0414 leads at 87.6% vs Qwen2.5-1M at 84.3%.