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.
93 models · page 1 of 2
Kimi
Kimi K3.1 Pro
66 benchmarks · 97 observations
Explore results →Kimi
K2 Horizon 375B A23B
22 benchmarks · 26 observations
Explore results →Kimi
Kimi K3
87 benchmarks · 170 observations
Explore results →Kimi
Kimi K3 (unknown)
8 benchmarks · 8 observations
Explore results →Kimi
Kimi K2.7 Code
28 benchmarks · 28 observations
Explore results →Kimi
Kimi K2.6
69 benchmarks · 87 observations
Explore results →Kimi
Kimi K2.6 (Reasoning)
4 benchmarks · 4 observations
Explore results →Kimi
Kimi K2.5
77 benchmarks · 114 observations
Explore results →Kimi
Kimi K2.5 (Fireworks)
4 benchmarks · 4 observations
Explore results →Kimi
Kimi K2.5 (instant)
1 benchmarks · 1 observations
Explore results →Kimi
Kimi K2.5 (Reasoning)
1 benchmarks · 1 observations
Explore results →Kimi
Kimi K2 Thinking
23 benchmarks · 27 observations
Explore results →Kimi
Kimi K2 Thinking Turbo
4 benchmarks · 4 observations
Explore results →Kimi
Kimi K2 Thinking (Together)
3 benchmarks · 3 observations
Explore results →Kimi
Kimi K2 Instruct (0905)
2 benchmarks · 2 observations
Explore results →Kimi
Kimi K2 (Sep 2025)
1 benchmarks · 1 observations
Explore results →Kimi
Kimi K2 0905 (Novita)
1 benchmarks · 1 observations
Explore results →Kimi
Kimi K2 Instruct
22 benchmarks · 25 observations
Explore results →Kimi
Kimi K2 (Jul 2025)
2 benchmarks · 2 observations
Explore results →Kimi
Kimi K2
4 benchmarks · 12 observations
Explore results →Microsoft
Phi-4 Mini
2 benchmarks · 2 observations
Explore results →Microsoft
Phi-4
9 benchmarks · 11 observations
Explore results →Microsoft
Phi-3.5-MoE
3 benchmarks · 3 observations
Explore results →Microsoft
Phi-3.5-mini
3 benchmarks · 3 observations
Explore results →Microsoft
Phi-3.5-vision-instruct
2 benchmarks · 2 observations
Explore results →Microsoft
phi-3-medium 14B
12 benchmarks · 15 observations
Explore results →Microsoft
phi-3-mini 3.8B
11 benchmarks · 14 observations
Explore results →Microsoft
phi-3-small 7.4B
10 benchmarks · 10 observations
Explore results →Microsoft
WizardLM-2 8x22B
3 benchmarks · 3 observations
Explore results →Microsoft
Phi-2
10 benchmarks · 14 observations
Explore results →Microsoft
Phi-1.5
6 benchmarks · 6 observations
Explore results →Microsoft
Phi-2 2.7b*
4 benchmarks · 4 observations
Explore results →Microsoft
phi-1.5-web (1.3B)
3 benchmarks · 3 observations
Explore results →Microsoft
phi-1.5-web-only (1.3B)
3 benchmarks · 3 observations
Explore results →Microsoft
Phi-3-mini-4k-instruct
3 benchmarks · 3 observations
Explore results →Kimi
Kimi K2.5 (Terminus 2)
2 benchmarks · 2 observations
Explore results →Kimi
Kimi K2.6 (Terminus 2)
2 benchmarks · 2 observations
Explore results →Kimi
Kimi K3 / Kimi Code
2 benchmarks · 3 observations
Explore results →Kimi
MoonShot-V1-8k†
2 benchmarks · 4 observations
Explore results →Microsoft
Phi-3-medium-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi-3-mini-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi3.5-Vision-4B
2 benchmarks · 3 observations
Explore results →Microsoft
wizardlm-13b / v1.2
2 benchmarks · 3 observations
Explore results →Kimi
; $0.363 per task; 103 median tokens per secondFireworksKimi K3 / Together AI
1 benchmarks · 1 observations
Explore results →Kimi
; $1.074 per task; 262 median tokens per secondFireworksKimi K3 / Baseten
1 benchmarks · 1 observations
Explore results →Kimi
; $5.426 per task; 70 median tokens per secondTogether AIKimi K3 / Fireworks
1 benchmarks · 1 observations
Explore results →Kimi
; $5.975 per task; 48 median tokens per secondFireworksKimi K3 / Moonshot
1 benchmarks · 1 observations
Explore results →Kimi
Kimi (Deep Think)
1 benchmarks · 1 observations
Explore results →