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 4 of 21
Reported model
Falcon-Instruct (7B)
3 benchmarks · 3 observations
Explore results →Reported model
GLaM (Dense) 0.1B
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (Dense) 1.7B
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (Dense) 137B
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (Dense) 8B
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (MoE) 0.1B/64E
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (MoE) 1.7B/64E
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (MoE) 64B/64E
3 benchmarks · 9 observations
Explore results →Reported model
GLaM (MoE) 8B/64E
3 benchmarks · 9 observations
Explore results →Reported model
internlm2-20b-reward
3 benchmarks · 3 observations
Explore results →Reported model
internlm2-7b-reward
3 benchmarks · 3 observations
Explore results →Reported model
InternVL2-26B
3 benchmarks · 3 observations
Explore results →Reported model
J1-Grande v1 (17B)
3 benchmarks · 3 observations
Explore results →Reported model
J1-Grande v2 beta (17B)
3 benchmarks · 3 observations
Explore results →Reported model
J1-Jumbo v1 (178B)
3 benchmarks · 3 observations
Explore results →Reported model
J1-Large v1 (7.5B)
3 benchmarks · 3 observations
Explore results →Reported model
Jurassic-2 Grande (17B)
3 benchmarks · 3 observations
Explore results →Reported model
Jurassic-2 Jumbo (178B)
3 benchmarks · 3 observations
Explore results →Reported model
Jurassic-2 Large (7.5B)
3 benchmarks · 3 observations
Explore results →Reported model
Llama 4-maverick-instruct-basic
3 benchmarks · 3 observations
Explore results →Reported model
LLaVA
3 benchmarks · 6 observations
Explore results →Reported model
LLaVA-OneVision-7B
3 benchmarks · 4 observations
Explore results →Reported model
Magicoder-S-CL-7B
3 benchmarks · 3 observations
Explore results →Reported model
mPLUG-Owl2
3 benchmarks · 4 observations
Explore results →Reported model
OpenChat-3.5-7B-0106
3 benchmarks · 3 observations
Explore results →Reported model
OpenCodeInterpreter-DS-33B
3 benchmarks · 3 observations
Explore results →Reported model
OpenCodeInterpreter-DS-6.7B
3 benchmarks · 3 observations
Explore results →Reported model
OpenHermes-2.5-Code-290k-13B
3 benchmarks · 3 observations
Explore results →Reported model
PaLM-cont 62B
3 benchmarks · 3 observations
Explore results →Reported model
speechless-coder-ds-6.7B
3 benchmarks · 3 observations
Explore results →Reported model
speechless-coding-7B-16k-tora
3 benchmarks · 3 observations
Explore results →Reported model
speechless-starcoder2-15b
3 benchmarks · 3 observations
Explore results →Reported model
speechless-starcoder2-7b
3 benchmarks · 3 observations
Explore results →Reported model
stable-code-3B
3 benchmarks · 3 observations
Explore results →Reported model
starchat2-15b-v0.1
3 benchmarks · 3 observations
Explore results →Reported model
StarCoder-15B
3 benchmarks · 3 observations
Explore results →Reported model
StarCoder2-15B
3 benchmarks · 3 observations
Explore results →Reported model
StarCoder2-3B
3 benchmarks · 3 observations
Explore results →Reported model
StarCoder2-7B
3 benchmarks · 3 observations
Explore results →Reported model
T5-Large
3 benchmarks · 4 observations
Explore results →Reported model
TNLG v2 (530B)
3 benchmarks · 3 observations
Explore results →Reported model
TNLG v2 (6.7B)
3 benchmarks · 3 observations
Explore results →Reported model
vicuna
3 benchmarks · 17 observations
Explore results →Reported model
vicuna-33b / v1.3
3 benchmarks · 6 observations
Explore results →Reported model
WaveCoder-Ultra-6.7B
3 benchmarks · 3 observations
Explore results →Reported model
WhiteRabbitNeo-33B-v1
3 benchmarks · 3 observations
Explore results →Reported model
WizardCoder-15B-V1.0
3 benchmarks · 3 observations
Explore results →Reported model
WizardCoder-Python-34B-V1.0
3 benchmarks · 3 observations
Explore results →