Rankings
Independent benchmark scores for models on Ageneral Models. Catalog.
Providers
Intelligence Index
Top 10 · Intelligence Index
Benchmark data from Artificial Analysis. Synced Jun 16, 2026.1.
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
anthropic55.7
2.
GPT-5.5 (xhigh)
openai54.8
3.
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
anthropic53.5
4.
GPT-5.4 (xhigh)
openai51.4
5.
Gemini 3.1 Pro Preview
gemini46.5
6.
Kimi K2.6
moonshot42.8
7.
GPT-5.2 (xhigh)
openai42.2
8.
GPT-5.1 (high)
openai38.9
9.
Kimi K2.5 (Reasoning)
moonshot38.1
10.
Grok 4.20 0309 (Reasoning)
xai36.5