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. | 22B | — |
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. | 32k | 128k |
| These models have no shared benchmark scores. | ||
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. | — | 74.1% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 50.6% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 51% |
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. | — | 81.3% |
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. | — | 90% |
| Overview | ||
| Company | Mistral | SpaceXSI |
| Release date | Sep 17 2024 | Mar 28 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mistral Small 2vsClaude Fable 5.2Grok‑1.5vsClaude Fable 5.2Mistral Small 2vsGPT-6.2 AstraGrok‑1.5vsGPT-6.2 AstraMistral Small 2vsGemini 4 HydrogenGrok‑1.5vsGemini 4 HydrogenMistral Small 2vsMuse EmberGrok‑1.5vsMuse EmberMistral Small 2vsDeepSeek-V4.1-Flash-1017Grok‑1.5vsDeepSeek-V4.1-Flash-1017Mistral Small 2vsKimi K3.1 ProGrok‑1.5vsKimi K3.1 ProFrequently asked questions
Mistral Small 2 and Grok‑1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Grok‑1.5 shipped 173 days before Mistral Small 2, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Mistral Small 2) vs 128k (Grok‑1.5). Mistral Small 2 is open weight, while Grok‑1.5 is closed.
Direct benchmark comparisons are unavailable — Mistral Small 2 and Grok‑1.5 don't publish scores on any of the same benchmarks.