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. | 1M | 128k |
| Benchmarks | ||
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. | 30% | 28.5% |
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. | — | 82.3% |
MATHReasoning — accuracy on the original competition mathematics test set | 77.9% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 51% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 67.3% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 62.3% | — |
| Overview | ||
| Company | Z.ai | |
| Release date | Sep 24 2024 | Jul 5 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 1.5 Flash-002vsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2Gemini 1.5 Flash-002vsGPT-6.2 AstraCodeGeeX4-ALL-9BvsGPT-6.2 AstraGemini 1.5 Flash-002vsMuse EmberCodeGeeX4-ALL-9BvsMuse EmberGemini 1.5 Flash-002vsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7Gemini 1.5 Flash-002vsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017Gemini 1.5 Flash-002vsMistral Large 4CodeGeeX4-ALL-9BvsMistral Large 4Frequently asked questions
Gemini 1.5 Flash-002 leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (LiveCodeBench). CodeGeeX4-ALL-9B shipped 81 days before Gemini 1.5 Flash-002, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 1.5 Flash-002) vs 128k (CodeGeeX4-ALL-9B). Gemini 1.5 Flash-002 is closed, while CodeGeeX4-ALL-9B is open weight.
On LiveCodeBench, Gemini 1.5 Flash-002 leads at 30% vs CodeGeeX4-ALL-9B at 28.5%.