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. | 200k | 32k |
| 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. | 84.9% | 9.8% |
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. | 88.2% | 45.2% |
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. | 95% | 25.9% |
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. | 22.2% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 6.9% |
HellaSwagReasoning — commonsense completion of short scenarios | — | 57% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 50.4% | — |
Okapi Multilingual MMLUMultilingual knowledge — five-shot accuracy on the Okapi translations of MMLU used in the Claude 3 model card | 79.1% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 90.7% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 59.4% | — |
| Overview | ||
| Company | Anthropic | Z.ai |
| Release date | Mar 4 2024 | Jun 25 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 3 OpusvsGPT-6.2 AstraChatGLM2-6BvsGPT-6.2 AstraClaude 3 OpusvsGemini 4 HydrogenChatGLM2-6BvsGemini 4 HydrogenClaude 3 OpusvsMuse EmberChatGLM2-6BvsMuse EmberClaude 3 OpusvsGrok 4.7ChatGLM2-6BvsGrok 4.7Claude 3 OpusvsDeepSeek-V4.1-Flash-1017ChatGLM2-6BvsDeepSeek-V4.1-Flash-1017Claude 3 OpusvsMistral Large 4ChatGLM2-6BvsMistral Large 4Frequently asked questions
Claude 3 Opus leads ChatGLM2-6B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). ChatGLM2-6B shipped 253 days before Claude 3 Opus, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude 3 Opus) vs 32k (ChatGLM2-6B). Claude 3 Opus is closed, while ChatGLM2-6B is open weight.
On HumanEval, Claude 3 Opus leads at 84.9% vs ChatGLM2-6B at 9.8%. On MMLU, Claude 3 Opus leads at 88.2% vs ChatGLM2-6B at 45.2%. On GSM8K, Claude 3 Opus leads at 95% vs ChatGLM2-6B at 25.9%.