Mistral AI
Mistral AI's frontier-class open-weight multimodal model optimized for agentic and coding use cases, with a 256K context window.
Running this yourself: likely needs a high-memory cloud gpu.
46.2
Quality Score
1198
Arena ELO
128B
Parameters
262K
Context
Sign in to join the discussion
0
Downloads
0
Likes
Apr 2026
Released
Launches
2
Benchmarks
19
Open Source
1
General
8
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 30.4/100 | Price: $3/M tokens | Output: 146.542 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 146.542 tok/s | HumanEval: 0.396%
View sourceQuality: 30.4/100 | Price: $3/M tokens | Output: 145.695 tok/s | HumanEval: 0.396%
View sourceQuality: 30.4/100 | Price: $3/M tokens | Output: 145.695 tok/s | HumanEval: 0.396%
View source☁️Mistral is bringing together the inference infrastructure, open models, and long-term commitments Europe needs to control its AI future, and setting a roadmap for the world. 🧵: https://t.co/LeP53uBUES https://t.co/JjluVwJecj

Mistral is announcing an expanded global strategic partnership with @Microsoft to give enterprises and regulated industries frontier AI they can control. As Mistral is expanding its AI compute capacity in Europe, the companies are expanding their strategic partnership with https://t.co/tfK6pt3Ixz
Quality: 30.4/100 | Price: $3/M tokens | Output: 145.695 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 145.695 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 139.812 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 130.919 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 122.163 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 121.852 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 125.102 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 117.22 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 120.488 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 131.399 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 133.881 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 138.775 tok/s | HumanEval: 0.396%
Quality: 30.4/100 | Price: $3/M tokens | Output: 138.775 tok/s | HumanEval: 0.396%
Quality: 29.9/100 | Price: $3/M tokens | Output: 138.775 tok/s | HumanEval: 0.396%
Quality: 29.9/100 | Price: $3/M tokens | Output: 136.315 tok/s | HumanEval: 0.396%
Quality: 29.9/100 | Price: $3/M tokens | Output: 166.089 tok/s | HumanEval: 0.396%
Quality: 29.9/100 | Price: $3/M tokens | Output: 81.07 tok/s | HumanEval: 0.396%
Quality: 29.9/100 | Price: $3/M tokens | Output: 110.666 tok/s | HumanEval: 0.396%
Mistral Medium 3.5 is now available through local Ollama runtime. 256K context window listed. Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.