MODEL DIRECTORY
Follow the model.
See the evidence.
Benchmark results, evaluation settings and disclosed training methods—collected in one place for each model.
3,335 reported models and checkpoint variants. Scores keep their original units and sources.
992 models · page 3 of 21
Technology Innovation Institute
Falcon-7B
14 benchmarks · 56 observations
Explore results →Reported model
stablelm-tuned-alpha-7b
6 benchmarks · 6 observations
Explore results →Reported model
vicuna-13b-v1.1
9 benchmarks · 9 observations
Explore results →Databricks
Dolly 2.0-12b
7 benchmarks · 8 observations
Explore results →Salesforce Research
BLIP-2 (Q-Former)
1 benchmarks · 1 observations
Explore results →Hugging Face,BigScience
BLOOM-176B
3 benchmarks · 3 observations
Explore results →Reported model
opt-13b
7 benchmarks · 8 observations
Explore results →Reported model
PaLM 62B
9 benchmarks · 13 observations
Explore results →DeepMind
Gopher (280B)
7 benchmarks · 22 observations
Explore results →Reported model
Hy4 Preview
24 benchmarks · 26 observations
Explore results →Reported model
Ling 3.0 Flash
17 benchmarks · 17 observations
Explore results →Reported model
Mercury 2.5
17 benchmarks · 17 observations
Explore results →Reported model
Ember-1
16 benchmarks · 16 observations
Explore results →Reported model
Mercury 3
11 benchmarks · 11 observations
Explore results →Reported model
Jamba 1.6 Large
10 benchmarks · 10 observations
Explore results →Reported model
Jamba 1.6 Mini
10 benchmarks · 10 observations
Explore results →Reported model
Vicuna-13B
9 benchmarks · 38 observations
Explore results →Reported model
Falcon-rw-1.3B
7 benchmarks · 7 observations
Explore results →Reported model
Vicuna 7B
7 benchmarks · 36 observations
Explore results →Reported model
Alpaca (7B)
6 benchmarks · 15 observations
Explore results →Reported model
vicuna-7b / v1.5
6 benchmarks · 10 observations
Explore results →Reported model
InternVL2-8B
5 benchmarks · 6 observations
Explore results →Reported model
Jamba 1.5 Large
5 benchmarks · 5 observations
Explore results →Reported model
Jamba 1.5 Mini
5 benchmarks · 5 observations
Explore results →Reported model
LLaVA-1.5-13B
5 benchmarks · 9 observations
Explore results →Reported model
LLaVA-1.5-7B
5 benchmarks · 9 observations
Explore results →Reported model
Magicoder-S-DS-6.7B
5 benchmarks · 6 observations
Explore results →Reported model
vicuna-13b / v1.5
5 benchmarks · 8 observations
Explore results →Reported model
XVERSE-13B
5 benchmarks · 5 observations
Explore results →Reported model
CodeGen-6B
4 benchmarks · 4 observations
Explore results →Reported model
MiniGPT-4
4 benchmarks · 10 observations
Explore results →Reported model
OpenCoder-8B-Instruct
4 benchmarks · 4 observations
Explore results →Reported model
PaLM 8B
4 benchmarks · 7 observations
Explore results →Reported model
SOLAR-10.7B-Instruct-v1.0
4 benchmarks · 4 observations
Explore results →Reported model
Starcoder2-15B-Instruct-v0.1
4 benchmarks · 4 observations
Explore results →Reported model
Yi-VL-34B
4 benchmarks · 6 observations
Explore results →Reported model
Zephyr β-7B
4 benchmarks · 5 observations
Explore results →Reported model
AquilaChat2 34B
3 benchmarks · 6 observations
Explore results →Reported model
Artigenz-Coder-DS-6.7B
3 benchmarks · 3 observations
Explore results →Reported model
BLOOMZ (7B)
3 benchmarks · 7 observations
Explore results →Reported model
Chinese-Alpaca-Plus-13B
3 benchmarks · 3 observations
Explore results →Reported model
code-millenials-34B
3 benchmarks · 3 observations
Explore results →Reported model
CodeGen-16B
3 benchmarks · 3 observations
Explore results →Reported model
CodeGen-2B
3 benchmarks · 3 observations
Explore results →Reported model
CodeT5+-16B
3 benchmarks · 3 observations
Explore results →Reported model
CodeT5+-2B
3 benchmarks · 3 observations
Explore results →Reported model
CodeT5+-6B
3 benchmarks · 3 observations
Explore results →Reported model
Composer 2.5 (Cursor CLI)
3 benchmarks · 3 observations
Explore results →