Magistral Small 1.2Aberto

Mistral · lançado 17 de set. de 2025

Mistral Magistral Small 1.2 model with 130K context window, optimized for advanced reasoning and multimodal tasks.

textimage130K ctx24 billion
65.0
Podium Score
#216 de 693
Intelligence Rank
65.0#216
AAQI: 30.0
Output Speed
60 t/s
TTFT: ~1.5s · ITL: 16.7 ms/tok
Blended Price (3:1)
$0.75 /1M
In: $0.5/M · Out: $1.5/M · Cache: $0.05
Context Capacity
130K
≈ 325 A4 Pages (Max Out: 8192)

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Magistral Small 1.2
Claude Mythos Preview (#1)
Average (68)
Coding (63)Mathematics (39)Hard Science (GPQA) (45)Agentic & Tool Use (36)Instruction Following (67)Vision / Multimodal (36)
API Deployment

Compare Multi-Host Hosting & Latency

Benchmark inference speed, TTFT latency distributions, and prompt cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, AWS Bedrock, and Azure.

View API Providers Matrix →

Pontuações por fonte

Pontuações por categoria

Resultados de benchmarks

Detalhes do modelo

Data de lançamento17 de set. de 2025
Parâmetros24 billion
LicençaOpen Weights
Janela de contexto130,000 tokens
Preço de entrada$0.5/M
Preço de saída$1.5/M
Velocidade de saída60 t/s
Tempo até o primeiro token2 ms

💰 Estimated Monthly Bill & TCO Calculator

Estimated Monthly Spend
$0.00
Calculating savings vs GPT-4o...

🔖 Embed Badges & Citation Snippet

GitHub Markdown Badge
[![LLMPodium Rank](https://llmpodium.com/badge/magistral-small-2509/rank.svg)](https://llmpodium.com/models/magistral-small-2509)
BibTeX Citation
@misc{llmpodium2026magistralsmall2509,
  title = {Benchmark Analysis and Intelligence Evaluation of Magistral Small 1.2},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/magistral-small-2509}
}

Confronto direto

Melhores modelos

model.alternatives_title

model.alternatives_desc

0 / 4 Models Selected