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. | — | 1.5B/7B/72B |
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. | 100k | 4k |
| Benchmarks | ||
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. | 86.7% | 96.7% |
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. | 58.7% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 84% |
Okapi Multilingual MMLUMultilingual knowledge — five-shot accuracy on the Okapi translations of MMLU used in the Claude 3 model card | 61.2% | — |
| Overview | ||
| Company | Anthropic | Qwen |
| Release date | Aug 9 2023 | Aug 8 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Instant 1.2vsGPT-6.2 AstraQwen2-MathvsGPT-6.2 AstraClaude Instant 1.2vsGemini 4 NeonQwen2-MathvsGemini 4 NeonClaude Instant 1.2vsMuse EmberQwen2-MathvsMuse EmberClaude Instant 1.2vsGrok 4.7Qwen2-MathvsGrok 4.7Claude Instant 1.2vsDeepSeek-V4.1-Flash-1017Qwen2-MathvsDeepSeek-V4.1-Flash-1017Claude Instant 1.2vsMistral Large 4Qwen2-MathvsMistral Large 4Frequently asked questions
Qwen2-Math leads Claude Instant 1.2 on 1 of the 1 benchmark they both report (GSM8K). Claude Instant 1.2 shipped 365 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude Instant 1.2) vs 4k (Qwen2-Math). Claude Instant 1.2 is closed, while Qwen2-Math is open weight.
On GSM8K, Qwen2-Math leads at 96.7% vs Claude Instant 1.2 at 86.7%.