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. | — | 30B |
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 | 200k |
| 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. | $0.40 | $0.00 |
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. | $1.60 | $0.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.10 | $0.00 |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.40Azure | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.60Azure | — |
| $160OpenAI list price | $0.00Z.ai list price | |
| Benchmarks | ||
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. | 23.6% | 59.2% |
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. | — | 64% |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | 31.6% | — |
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. | 93.8% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 84.1% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 42.8% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 81.4% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 81 | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 49.6% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 91.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 16.8% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | 78.5% | — |
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. | 87.5% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 88.2% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 56.8% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 73.1% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 72.7% | — |
GraphWalks BFS (<128K)Long context — breadth-first traversal accuracy for inputs shorter than 128K tokens | 61.7% | — |
GraphWalks parents (<128K)Long context — parent-node retrieval accuracy for inputs shorter than 128K tokens | 60.5% | — |
OpenAI MRCR (2 needles) · 128KLong context — retrieval of two matching turns in the original MRCR evaluation | 47.2% | — |
OpenAI MRCR (2 needles) · 1MLong context — retrieval of two matching turns in the original MRCR evaluation | 33.3% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Apr 14 2025 | Jan 19 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
GPT-4.1 minivsClaude Fable 5.2GLM-4.7-FlashvsClaude Fable 5.2GPT-4.1 minivsGemini 4 HydrogenGLM-4.7-FlashvsGemini 4 HydrogenGPT-4.1 minivsMuse EmberGLM-4.7-FlashvsMuse EmberGPT-4.1 minivsGrok 4.7GLM-4.7-FlashvsGrok 4.7GPT-4.1 minivsDeepSeek-V4.1-Flash-1017GLM-4.7-FlashvsDeepSeek-V4.1-Flash-1017GPT-4.1 minivsMistral Large 4GLM-4.7-FlashvsMistral Large 4Frequently asked questions
GLM-4.7-Flash leads GPT-4.1 mini on 1 of the 1 benchmark they both report (SWE-Bench Verified). GLM-4.7-Flash is cheaper on both input and output: $0.00 vs $0.40 per million input tokens, and $0.00 vs $1.60 per million output tokens. GPT-4.1 mini shipped 280 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (GPT-4.1 mini) vs 200k (GLM-4.7-Flash). GPT-4.1 mini is closed, while GLM-4.7-Flash is open weight.
On SWE-Bench Verified, GLM-4.7-Flash leads at 59.2% vs GPT-4.1 mini at 23.6%.