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. | — | 9B |
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. | 128k | 128k |
| 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. | 83.7% | 82.3% |
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. | — | 28.5% |
MATHReasoning — accuracy on the original competition mathematics test set | 64.3% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 83.2 | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 42.5% | — |
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. | 84.7% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 87.1% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Nov 6 2023 | Jul 5 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
GPT-4 TurbovsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2GPT-4 TurbovsGemini 4 HydrogenCodeGeeX4-ALL-9BvsGemini 4 HydrogenGPT-4 TurbovsMuse EmberCodeGeeX4-ALL-9BvsMuse EmberGPT-4 TurbovsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7GPT-4 TurbovsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017GPT-4 TurbovsMistral Large 4CodeGeeX4-ALL-9BvsMistral Large 4Frequently asked questions
GPT-4 Turbo leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). GPT-4 Turbo shipped 242 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (GPT-4 Turbo) vs 128k (CodeGeeX4-ALL-9B). GPT-4 Turbo is closed, while CodeGeeX4-ALL-9B is open weight.
On HumanEval, GPT-4 Turbo leads at 83.7% vs CodeGeeX4-ALL-9B at 82.3%.