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. | 12B | — |
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 | — |
| 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. | 72% | 85.7% |
MATHReasoning — accuracy on the original competition mathematics test set | 48.1% | 73% |
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. | 69.2% | 86.2% |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 58% | 68.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 52.5% | 63.2% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 61.3% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 72% |
| Overview | ||
| Company | Mistral | SpaceXSI |
| Release date | Sep 11 2024 | Aug 13 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Pixtral 24.09vsClaude Fable 5.2Grok‑2 minivsClaude Fable 5.2Pixtral 24.09vsGPT-6.2 AstraGrok‑2 minivsGPT-6.2 AstraPixtral 24.09vsGemini 4 HydrogenGrok‑2 minivsGemini 4 HydrogenPixtral 24.09vsMuse EmberGrok‑2 minivsMuse EmberPixtral 24.09vsDeepSeek-V4.1-Flash-1017Grok‑2 minivsDeepSeek-V4.1-Flash-1017Pixtral 24.09vsKimi K3.1 ProGrok‑2 minivsKimi K3.1 ProFrequently asked questions
Grok‑2 mini leads Pixtral 24.09 on 5 of the 5 benchmarks they both report. Grok‑2 mini shipped 29 days before Pixtral 24.09, so benchmark comparisons should account for the intervening progress.
Pixtral 24.09 is open weight, while Grok‑2 mini is closed.
On HumanEval, Grok‑2 mini leads at 85.7% vs Pixtral 24.09 at 72%. On MATH, Grok‑2 mini leads at 73% vs Pixtral 24.09 at 48.1%. On MMLU, Grok‑2 mini leads at 86.2% vs Pixtral 24.09 at 69.2%. On MathVista, Grok‑2 mini leads at 68.1% vs Pixtral 24.09 at 58%. On MMMU, Grok‑2 mini leads at 63.2% vs Pixtral 24.09 at 52.5%.