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. | 124B | — |
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 | ||
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 69.4% | 68.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 64% | 63.2% |
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. | — | 85.7% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 73% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 72% |
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. | — | 86.2% |
| Overview | ||
| Company | Mistral | SpaceXSI |
| Release date | Nov 18 2024 | Aug 13 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Pixtral Large 24.11vsClaude Fable 5.2Grok‑2 minivsClaude Fable 5.2Pixtral Large 24.11vsGPT-6.2 AstraGrok‑2 minivsGPT-6.2 AstraPixtral Large 24.11vsGemini 4 HydrogenGrok‑2 minivsGemini 4 HydrogenPixtral Large 24.11vsMuse EmberGrok‑2 minivsMuse EmberPixtral Large 24.11vsDeepSeek-V4.1-Flash-1017Grok‑2 minivsDeepSeek-V4.1-Flash-1017Pixtral Large 24.11vsKimi K3.1 ProGrok‑2 minivsKimi K3.1 ProFrequently asked questions
Pixtral Large 24.11 leads Grok‑2 mini on 2 of the 2 benchmarks they both report (MathVista, MMMU). Grok‑2 mini shipped 97 days before Pixtral Large 24.11, so benchmark comparisons should account for the intervening progress.
Pixtral Large 24.11 is open weight, while Grok‑2 mini is closed.
On MathVista, Pixtral Large 24.11 leads at 69.4% vs Grok‑2 mini at 68.1%. On MMMU, Pixtral Large 24.11 leads at 64% vs Grok‑2 mini at 63.2%.