Mistral NeMo Instruct
Mistral AIMistralOpen WeightApache 2.0 · Commercial OK
Description
A state-of-the-art 12B multilingual model with a 128k context window, designed for global applications and strong in multiple languages.
Release Date
2024-07-18
Parameters
12.0B
Context Length
128K
Modalities
text
Capability Radar
60
general
0
coding
70
reasoning
51
scienceest.
49
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
TriviaQA
73.8%SR
MMLU
68.0%SR
TruthfulQA
50.3%SR
Reasoning
HellaSwagAI2 (2019)
83.5%SR
Winogrande
76.8%SR
CommonSenseQA
70.4%SR
OpenBookQA
60.6%SR
Natural Questions
31.2%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Language70
Math70
Legal60
Reasoning60
Finance60
General60
Healthcare60
Search30
Pricing
Input Price$0 / 1M tokens
Output Price$0 / 1M tokens
Blended Price (3:1)$0 / 1M tokens
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
7 providers
Cheapest: Mistral AIMost Expensive: Helicone
ProviderInputOutput
1Mistral AIPRIMARY
$0
$0
2DeepInfra
$0
$0
3OVHcloud AI Endpoints
$0.14
$0.14
4Cortecs
$0.145
$0.145
5Mistral
$0.15
$0.15
6DigitalOcean
$0.3
$0.3
7Helicone
$20
$40
Compare pricing across different API providers for this model.