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.
261 models · page 1 of 6
MiniMax
MiniMax M3.1 Flash
37 benchmarks · 95 observations
Explore results →Meta
Muse Spark Open
44 benchmarks · 109 observations
Explore results →Meta
Muse Spark Open (unknown)
1 benchmarks · 1 observations
Explore results →Meta
Muse Wonder
52 benchmarks · 128 observations
Explore results →Meta
Muse Wonder Full
31 benchmarks · 93 observations
Explore results →Meta
Muse Wonder (unknown)
3 benchmarks · 3 observations
Explore results →Meta
Muse Wonder (minimal)
1 benchmarks · 1 observations
Explore results →StepFun
Step 5 Preview
44 benchmarks · 52 observations
Explore results →StepFun
Step 5 Preview (unknown)
3 benchmarks · 3 observations
Explore results →Meta
Muse Spark 1.3
47 benchmarks · 78 observations
Explore results →Meta
Muse Spark 1.3 (unknown)
5 benchmarks · 5 observations
Explore results →Meta
Muse Spark 1.3 (minimal)
2 benchmarks · 4 observations
Explore results →Meta
Muse Glimmer
3 benchmarks · 3 observations
Explore results →Meta
Muse Spark 1.2
44 benchmarks · 47 observations
Explore results →Meta
Muse Spark 1.1
43 benchmarks · 47 observations
Explore results →MiniMax
MiniMax M3
53 benchmarks · 67 observations
Explore results →StepFun
Step 3.7 Flash
4 benchmarks · 4 observations
Explore results →Meta
Muse Spark
31 benchmarks · 33 observations
Explore results →MiniMax
MiniMax M2.7
30 benchmarks · 32 observations
Explore results →MiniMax
MiniMax M2.5
25 benchmarks · 26 observations
Explore results →MiniMax
MiniMax M2.1
18 benchmarks · 21 observations
Explore results →MiniMax
MiniMax M2
4 benchmarks · 4 observations
Explore results →MiniMax
MiniMax M1 80k
2 benchmarks · 2 observations
Explore results →MiniMax
MiniMax M1 40k
1 benchmarks · 1 observations
Explore results →Meta
Llama 4 Maverick
43 benchmarks · 65 observations
Explore results →Meta
Llama 4 Scout
28 benchmarks · 39 observations
Explore results →Meta
Llama 4 Maverick (FP8)
4 benchmarks · 4 observations
Explore results →Meta
Llama 3.3 70B
16 benchmarks · 17 observations
Explore results →Meta
Llama 3.2 90B
8 benchmarks · 8 observations
Explore results →Meta
Llama 3.2 1B
5 benchmarks · 5 observations
Explore results →Meta
Llama 3.2 3B
3 benchmarks · 3 observations
Explore results →Meta
Llama 3.2 11B
2 benchmarks · 2 observations
Explore results →Meta
Dracarys2-Llama-3.1-70B-Instruct
1 benchmarks · 1 observations
Explore results →Meta
Llama 3.1-405B
22 benchmarks · 26 observations
Explore results →Meta
Llama 3.1-8B
22 benchmarks · 30 observations
Explore results →Meta
Llama 3.1-70B
19 benchmarks · 22 observations
Explore results →Meta
Hermes 2 Theta Llama-3 70B
3 benchmarks · 3 observations
Explore results →Meta
Llama 3-70B
25 benchmarks · 64 observations
Explore results →Meta
Llama 3-8B
23 benchmarks · 46 observations
Explore results →Meta
Llama 2-70B
25 benchmarks · 85 observations
Explore results →Meta
Llama 2-7B
23 benchmarks · 97 observations
Explore results →Meta
Llama 2-13B
22 benchmarks · 90 observations
Explore results →Meta
Llama 2-34B
10 benchmarks · 26 observations
Explore results →Meta
Llama 13B
17 benchmarks · 50 observations
Explore results →Meta
Llama 7B
16 benchmarks · 65 observations
Explore results →Meta
Llama 65B
15 benchmarks · 42 observations
Explore results →Meta
Llama 33B
12 benchmarks · 37 observations
Explore results →Meta
OPT-1.3B
6 benchmarks · 6 observations
Explore results →