AI Leaderboard — Compare 300+ Top AI Models by Intelligence, Speed & Price
Independent rankings of GPT, Claude, Gemini, Llama, DeepSeek and 300+ AI models — composite LLM Stats Score, updated continuously from public benchmarks and live API metrics. See the full LLM Leaderboard for complete LLM rankings with advanced filters.
leads on reasoning
Claude Mythos Preview
94.6%gpqa
wins at coding
GPT-5.5
21arena
cheapest in the top 10
Qwen3.7 Max
$1.25/M tok
fastest output
Grok-4 Fast Non-Reasoning
709tok/s
longest context window
Grok 4 Fast
2.0M tokenstokens
best open-weights
GLM-5.2
91.2%gpqa
319
| License | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
1 | 65.2 | 70.2 | 56.0 | 46.4 | — | — | — | — | Proprietary | |
2 | 63.2 | 55.3 | — | 28.4 | — | — | — | — | Proprietary | |
3 | 61.3 | 63.1 | 52.3 | 44.0 | 1,571 | 1.0M | 51c/s | $7.22 | Proprietary | |
4 | 59.0 | 59.0 | 49.4 | 39.9 | 1,005 | 1.0M | 18c/s | $1.73 | Open Source | |
5 | 58.5 | 66.3 | 58.9 | 50.2 | 1,899 | — | 17c/s | — | Proprietary | |
6 | 57.3 | 54.2 | 42.5 | 36.2 | 1,740 | 1.0M | 189c/s | $3.89 | Proprietary | |
7 | 56.2 | 58.9 | 49.8 | 40.1 | 2,131 | 1.1M | 32c/s | $7.78 | Proprietary | |
8 | 56.1 | 47.4 | 30.5 | — | 1,250 | 400K | 327c/s | $2.22 | Proprietary | |
9 | 55.5 | 52.3 | 31.9 | 28.0 | — | — | — | — | Proprietary | |
10 | 55.3 | 48.1 | 30.0 | — | 991 | 400K | 411c/s | $2.22 | Proprietary | |
11 | 54.4 | 57.5 | 47.1 | 37.5 | 1,680 | 1.0M | 15c/s | $1.53 | Proprietary | |
12 | 53.8 | 57.6 | 48.4 | 40.8 | 1,926 | 1.0M | 37c/s | $7.22 | Proprietary | |
13 | 53.7 | 43.2 | — | — | 1,101 | — | — | — | Proprietary | |
14 | 53.2 | 55.1 | 45.3 | 39.7 | 1,633 | 1.0M | 230c/s | $2.33 | Proprietary | |
15 | 53.1 | 55.7 | 42.3 | 32.0 | 2,111 | 1.0M | 65c/s | $3.89 | Proprietary |
1-15 of 319