LLM Leaderboard

Ranked models

Compare quality, speed, latency, and cost across available models.

#ModelOverall Score↓Quality (80%)Performance (20%)
Arena ELO40% weightArtificial Analysis Intelligence Index40% weightSpeed10% weightLatency10% weight
1
GPT-6.1 Sol icon
GPT-6.1 Sol
OpenAI
0.851
1,484
51.8
108.5 t/s
3.01s
2
Muse Spark 1.3 icon
Muse Spark 1.3
Meta
0.843
1,494
48.1
73.0 t/s
3.78s
3
Kimi K3 icon
Kimi K3
Moonshot
0.809
1,488
43.6
97.0 t/s
1.52s
4
Gemini 3.8 Flash icon
Gemini 3.8 Flash
Google
0.805
1,497
40.9
104.0 t/s
3.04s
5
GLM 5.3 Flash icon
GLM 5.3 Flash
Z.ai
0.780
1,475
41.8
236.0 t/s
0.64s
6
DeepSeek V4.1 Flash icon
DeepSeek V4.1 Flash
DeepSeek
0.776
1,475
39.5
340.0 t/s
0.42s
7
MiMo-V2.6-Pro icon
MiMo-V2.6-Pro
Xiaomi
0.775
1,480
46.3
31.0 t/s
4.62s
8
qwen3.8-max icon
qwen3.8-max
Alibaba
0.761
1,483
40.2
49.0 t/s
1.62s
9
GPT-5.5 icon
GPT-5.5
OpenAI
0.743
1,482
38.4
86.0 t/s
2.49s
10
GPT-5.6 Terra icon
GPT-5.6 Terra
OpenAI
0.739
1,466
42.1
100.0 t/s
0.45s
11
Gemini 3.1 Pro Preview icon
Gemini 3.1 Pro Preview
Google
0.690
1,487
29.7
104.0 t/s
2.86s
12
GLM 5.2 icon
GLM 5.2
Z.ai
0.689
1,475
27.9
368.0 t/s
0.63s
13
Grok 4.7 icon
Grok 4.7
SpaceXAI
0.681
1,443
46.4
57.0 t/s
2.76s
14
GPT-6 Luna icon
GPT-6 Luna
OpenAI
0.630
1,443
38.1
114.0 t/s
1.87s
15
Qwen3.8 27B icon
Qwen3.8 27B
Alibaba
0.618
1,438
33.7
334.0 t/s
0.50s

About these metrics

Score

Composite score (0–1) blending the selected category’s quality metrics with speed and latency. Higher is better, relative to the models currently listed.

Quality (80%)

Arena ELO
Chatbot Arena ELO overall rating.40% weight
Artificial Analysis Intelligence Index
Measures general reasoning and knowledge capabilities.40% weight

Performance (20%)

Speed
Output throughput in tokens per second from the fastest available provider.10% weight
Latency
Time to first token in seconds — lower is better.10% weight

Use the + in the table header to view additional reference benchmarks and pricing metrics.

0 / 6 selected