HF Model & Benchmark Matrix

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

internlm2-math-plus-7b

internlm/internlm2-math-plus-7b

kind
original
quant
bf16 (16-bit)
family
internlm
modality
text-generation
root model
internlm/internlm2-math-plus-7b
provider
internlm
license
other
language
en, zh
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
356
likes
11
created
—
last modified
2025-03-13T07:04:50+00:00 (2025)
huggingface
https://huggingface.co/internlm/internlm2-math-plus-7b
tags
transformerssafetensorsinternlm2text-generationmathconversationalcustom_codeenzharxiv:2402.06332license:othereval-resultsregion:us

Benchmark scores (12)

benchmarkcategoryscorecontextconfevidence
GSM8Kmath85.8high| InternLM2-Math-Plus-7B | **53.0** | **59.7** | 85.8 |
MATHmath53.0high| InternLM2-Math-Plus-7B | **53.0** | **59.7** | 85.8 |
MATHmath51.7Deepseek-Math-7B-RLmedium| Deepseek-Math-7B-RL | 51.7 | 58.8 | **88.2** |
miniF2Fmath43.4high| InternLM2-Math-Plus-7B | **43.4** |
MATHmath43.4InternLM2-Math-Plus-7Bmedium| InternLM2-Math-Plus-7B | **43.4** |
MATHmath42.6InternLM2-Math-Plus-20Bmedium| InternLM2-Math-Plus-20B | 42.6 |
MATHmath38.9InternLM2-Math-Plus-1.8Bmedium| InternLM2-Math-Plus-1.8B | 38.9 |
MATHmath37.7InternLM2-Math-20Bmedium| InternLM2-Math-20B | 37.7 | 54.3 | 82.6 |
MATHmath37.3InternLM2-Math-Plus-Mixtral8x22Bmedium| InternLM2-Math-Plus-Mixtral8x22B | 37.3 |
MATHmath34.6InternLM2-Math-7Bmedium| InternLM2-Math-7B | 34.6 | 50.9 | 78.1 |
MATHmath30.3InternLM2-Math-7B-Basemedium| InternLM2-Math-7B-Base | 30.3 |
MATHmath29.5InternLM2-Math-20B-Basemedium| InternLM2-Math-20B-Base | 29.5 |

Discussions (0)

none scraped.

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