Home/Benchmarks/AA Intelligence Index v5

AA Intelligence Index v5

Intelligence index · 20 models · source Artificial Analysis · updated 2026-10-27

GPQA DiamondTerminal-Bench 4.0LiveBench DesignVals IndexAA Intelligence Index v4.3.2
What this benchmark measures

A weighted composite of 10 independent evaluations covering knowledge, reasoning, coding, agents and long-horizon tasks. v5 went live on 27 October with a stricter scale than v4.3.2; scores from the two versions are not comparable.

Why it gets its own table

The only composite independent index that covers closed and open models and refreshes every two weeks. Its weakness is that the weights are not public, so this site uses it as the primary sort while showing the component scores alongside.

Full ranking

#ModelScoreVs. bestInput $Output $Type
1 Gemini 4 CarbonGoogle 60.0 Best overall $4.00 $20.00
2 Claude Opus 5.5Anthropic 59.1 98% $4.00 $20.00
3 GPT-6 AstraOpenAI 56.9 95% $10.00 $50.00
4 GPT-6.1 SolOpenAI 54.6 91% $2.00 $10.00
5 Claude Sonnet 5.5Anthropic 54.5 91% $2.00 $10.00
6 GPT-6.1 TerraOpenAI 51.3 86% $1.00 $5.00
7 Gemini 4 ArgonGoogle 50.4 84% $2.00 $10.00
8 Muse Wonder FullMeta 50.0 83% — —
9 Claude Fable 5.1Anthropic 49.0 82% $10.00 $50.00
10 Kimi K3.1 Pro Open weightsMoonshot AI 46.0 77% $2.00 $10.00 Open weights
11 Muse WonderMeta 44.0 73% $4.00 $20.00
12 Claude Haiku 5.5Anthropic 36.0 60% $0.10 $0.50
13 Grok 4.7xAI 34.3 57% $2.00 $6.00
14 Qwen3.8 MaxAlibaba Qwen 34.0 57% $2.00 $6.00
15 DeepSeek V4.1 Flash Open weightsDeepSeek 33.0 55% $0.30 $1.20 Open weights
16 GLM-5.3 Open weightsZ.ai 32.0 53% $1.40 $4.40 Open weights
17 MiMo-V2.6 Pro Open weightsXiaomi 30.0 50% $0.35 $1.40 Open weights
18 MiniMax M3.1 FlashMiniMax 29.0 48% $0.15 $0.60
19 Mistral Large 4 Open weightsMistral 26.0 43% $0.70 $2.10 Open weights
20 DeepSeek V4 Pro Open weightsDeepSeek 23.0 38% $1.32 $3.96 Open weights