Benchmarks · composite
AA Intelligence Index v5.0
Artificial Analysis' composite intelligence score (v5.0), combining 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1.
32 models · 79 results · data as of 2026-11-06 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Carbon high
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 17 more models under All models in settings.
More from this benchmark
14 published measuresOutput tokens per task92 results · lower is better
18 more models under All models in settings.
Score vs any published measure13 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | ||||||||
|---|---|---|---|---|---|---|---|---|
| Gemini 4 Carbon high | 7.76 | 5.3 | 0.047 | 2.04 | 3.21 | 2.46 | 1.44 | 1.01 |
| Opus 5.5 max | 10.0 | 6.57 | 0.0357 | 4.74 | 1.8 | 3.47 | 2.41 | 1.06 |
| GPT-6 Astra max | 6.24 | 3.65 | 0.0815 | 2.17 | 1.39 | 2.6 | 1.79 | 0.811 |
| GPT-6.1 Sol max | 1.27 | 0.594 | 0.0163 | 0.252 | 0.326 | 0.678 | 0.492 | 0.186 |
| Sonnet 5.5 max | 10.0 | 7.17 | 0.0178 | 4.88 | 2.27 | 2.85 | 2.06 | 0.79 |
| GPT-6.1 Terra max | 0.961 | 0.662 | 0.00815 | 0.426 | 0.227 | 0.299 | 0.197 | 0.103 |
| Gemini 4 Argon high | 7.68 | 5.36 | 0.0245 | 2.07 | 3.26 | 2.33 | 1.37 | 0.961 |
| Fable 5.1 xhigh | 10.8 | 6.07 | 0.0875 | 3.06 | 2.92 | 4.78 | 2.75 | 2.03 |
| Kimi K3.1 max | 3.68 | 2.96 | 0.0167 | 2.1 | 0.84 | 0.722 | 0.442 | 0.28 |
| Muse Wonder (Max) | 6.95 | 5.03 | 0.0253 | 3.79 | 1.22 | 1.92 | 1.17 | 0.75 |
| Muse Spark 1.3 max | 2.39 | 2 | 0.00792 | 1.71 | 0.277 | 0.387 | 0.232 | 0.156 |
| Haiku 5.5 max | 0.411 | 0.298 | 0.000888 | 0.233 | 0.0646 | 0.113 | 0.0864 | 0.0266 |
| Grok 4.7 xhigh | 7.77 | 7.14 | 0.0117 | 4.57 | 2.57 | 0.627 | 0.417 | 0.211 |
| DeepSeek V4.1 Flash 1017 max | 0.602 | 0.435 | 0.00115 | 0.178 | 0.256 | 0.167 | 0.109 | 0.058 |
| GLM 5.3 max | 5.01 | 4.49 | 0.00248 | 4.13 | 0.349 | 0.524 | 0.373 | 0.151 |
| Gemini 3.8 Flash high | 7.77 | 7.39 | 0.0031 | 0.364 | 7.03 | 0.371 | 0.225 | 0.146 |
| MiMo V2.6 Pro | 0.257 | 0.152 | 0.000828 | 0.0428 | 0.108 | 0.105 | 0.0751 | 0.0303 |
| GPT-6 Luna max | 0.152 | 0.114 | 0.000815 | 0.0896 | 0.0239 | 0.0376 | 0.0288 | 0.00887 |
| GLM 5.3 Flash max | 0.583 | 0.516 | 0.00121 | 0.476 | 0.0386 | 0.0671 | 0.0513 | 0.0158 |
| MiMo V2.6 Flash | 0.129 | 0.0916 | 0.000939 | 0.0484 | 0.0422 | 0.0369 | 0.0279 | 0.00899 |
| Mistral Large 4 high | 2.06 | 1.89 | 0.0045 | 0.782 | 1.1 | 0.172 | 0.114 | 0.0576 |
| Muse Spark Open xhigh | 2.02 | 1.74 | 0.00796 | 1.1 | 0.632 | 0.282 | 0.137 | 0.145 |
| DeepSeek V4 Pro 0813 max | 1.77 | 1.38 | 0.00229 | 0.905 | 0.471 | 0.391 | 0.24 | 0.151 |
| Qwen 3.8 27B xhigh | 3.53 | 3.2 | 0.00317 | 1.18 | 2.02 | 0.329 | 0.217 | 0.112 |
| MiniMax M3 | 1.29 | 1.18 | 0.00222 | 0.951 | 0.222 | 0.11 | 0.0553 | 0.0545 |
All results
79 rows| # | Model | Effort | Score | Subscription $ / task | API $ / task | Output tokens |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 59.4 | $2.76 | $7.76 | 123k |
| 2 | Opus 5.5 | max | 58.4 | $0.15 | $10 | 173k |
| 3 | Gemini 4 Carbon | medium | 57.7 | $2.35 | $6.59 | 103k |
| 4 | Opus 5.5 | xhigh | 57.0 | $0.092 | $6.05 | 103k |
| 5 | GPT-6 Astra | max | 56.9 | $0.27 | $6.24 | 52k |
| 6 | GPT-6 Astra | xhigh | 55.3 | $0.16 | $3.66 | 27k |
| 7 | GPT-6 Astra | high | 54.8 | $0.14 | $3.24 | 23k |
| 8 | GPT-6.1 Sol | max | 54.5 | $0.074 | $1.27 | 68k |
| 9 | Sonnet 5.5 | max | 54.2 | $0.15 | $10 | 285k |
| 10 | Gemini 4 Carbon | low | 53.7 | |||
| 11 | GPT-6.1 Sol | xhigh | 52.3 | $0.045 | $0.76 | 30k |
| 12 | Opus 5.5 | high | 51.7 | $0.052 | $3.46 | 60k |
| 13 | GPT-6 Astra | medium | 51.5 | $0.12 | $2.73 | 18k |
| 14 | GPT-6.1 Terra | max | 51.0 | $0.049 | $0.96 | 60k |
| 15 | Gemini 4 Argon | high | 50.4 | $5.48 | $7.68 | 116k |
| 16 | GPT-6.1 Sol | high | 50.2 | $0.034 | $0.59 | 23k |
| 17 | Fable 5.1 | xhigh | 49.7 | $1.69 | $11 | 97k |
| 18 | Sonnet 5.5 | xhigh | 49.6 | $0.062 | $4.09 | 122k |
| 19 | Fable 5.1 | max | 49.0 | $2.03 | $13 | 118k |
| 20 | Opus 5.5 | medium | 48.1 | $0.037 | $2.45 | 44k |
| 21 | Fable 5.1 | high | 47.0 | $1.18 | $7.54 | 66k |
| 22 | GPT-6.1 Sol | medium | 46.1 | $0.021 | $0.36 | 14k |
| 23 | Kimi K3.1 | max | 46.0 | $3.68 | $3.68 | 72k |
| 24 | GPT-6.1 Terra | xhigh | 45.0 | $0.020 | $0.40 | 26k |
| 25 | Muse Wonder (Max) | max | 43.3 | $4.63 | $6.95 | 96k |
| 26 | GPT-6 Astra | low | 43.0 | $0.061 | $1.42 | 9.1k |
| 27 | Fable 5.1 | medium | 43.0 | $0.87 | $5.56 | 49k |
| 28 | GPT-6.1 Terra | high | 42.3 | $0.013 | $0.26 | 17k |
| 29 | Sonnet 5.5 | high | 41.1 | $0.025 | $1.64 | 58k |
| 30 | Fable 5.1 | low | 38.5 | $0.70 | $4.47 | 38k |