HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Mistral-Large-Instruct-2407

mistralai/Mistral-Large-Instruct-2407

kind
original
quant
bf16 (16-bit)
family
mistral
modality
—
root model
mistralai/Mistral-Large-Instruct-2407
provider
mistralai
license
other
language
en, fr, de, es, it, pt, zh, ja, ru, ko
context
—
library
vllm
vRAM (GB)
—
size on disk
—
downloads
4,852
likes
865
created
—
last modified
2025-07-28T17:16:38+00:00 (2025)
huggingface
https://huggingface.co/mistralai/Mistral-Large-Instruct-2407
tags
vllmsafetensorsmistralmistral-commonenfrdeesitptzhjarukolicense:othereval-resultsregion:us

Benchmark scores (9)

benchmarkcategoryscorecontextconfevidence
GSM8Kmath93.0GSM8Kmedium| GSM8K | 93% |
MMLUknowledge84.0MMLUmedium| MMLU | 84.0% |
MBPPcoding80.0MBPP Basemedium| MBPP Base | 80% |
Chatbot Arenachat73.2Arena Hardmedium| Arena Hard | 73.2 |
MATHmath71.5Math Instruct (0-shot, CoT)medium| Math Instruct (0-shot, CoT) | 71.5% |
MATHmath70.0Math Instruct (0-shot, no CoT)medium| Math Instruct (0-shot, no CoT) | 70% |
MBPPcoding69.0MBPP Plusmedium| MBPP Plus | 69% |
WildBenchchat56.3Wild Benchmedium| Wild Bench | 56.3 |
MT-Benchchat8.63MT Benchmedium| MT Bench | 8.63 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.