Mistral Small 3.2 24B Instruct by Mistral AI scores 18.9 out of 100 on the Neura Intelligence Index, ranking #306 among tracked AI models. This composite score is computed from 3 individual benchmarks across coding, math, reasoning, and language categories.

Mistral Small 3.2 24B Instruct costs $0.075/1M input tokens and $0.2/1M output tokens via API. At a typical 3:1 input-to-output ratio with 1M tokens/day usage, the estimated monthly cost is approximately $3.

Yes, Mistral Small 3.2 24B Instruct has open weights available under the apache_2_0 license. You can download and self-host the model.

Mistral Small 3.2 24B Instruct supports a context window of 128K tokens, allowing it to process moderate-length documents and conversations in a single request.

Mistral Small 3.2 24B Instruct achieves its highest score on MMMU with a score of 62.5%. This benchmark evaluates massive multi-discipline multimodal understanding — college-level multimodal questions.