Meta Models: Intelligence, Performance & Price
Muse Wonder Full (max)Muse Wonder (max)Muse Spark 1.3 (max)Muse Spark 1.3 (xhigh)Muse Spark Open (xhigh)Artificial Analysis Intelligence Index
Artificial Analysis has benchmarked 25 models from Meta. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from Meta is Muse Wonder Full (Max) at 56.
- For output speed, the fastest model is Muse Spark 1.3 (Xhigh) at 294 t/s.
- For latency, Llama 4 Scout at 0.96s offers the lowest time to first answer token.
- For pricing, Llama 4 Maverick at $0.04 offers the lowest cost per task. Prices vary up to 118x across models.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
All Meta Releases
Muse Spark Open
1 model
39
Highest Intelligence
Muse Wonder
1 model
52
Highest Intelligence
Muse Wonder Full
1 model
56
Highest Intelligence
Muse Spark 1.3
2 models
48
Highest Intelligence
Muse Glimmer
1 model
17
Highest Intelligence
Muse Spark 1.2
1 model
40
Highest Intelligence
Muse Spark 1.1
1 model
34
Highest Intelligence
Muse Spark
1 model
31
Highest Intelligence
Llama 4 Maverick
1 model
9
Highest Intelligence
Llama 4 Scout
1 model
6
Highest Intelligence
Llama 3.3 Instruct 70B
1 model
8
Highest Intelligence
Llama 3.2 Instruct 11B (Vision)
1 model
5
Highest Intelligence
Llama 3.2 Instruct 1B
1 model
5
Highest Intelligence
Llama 3.2 Instruct 3B
1 model
6
Highest Intelligence
Llama 3.2 Instruct 90B (Vision)
1 model
6
Highest Intelligence
Llama 3.1 Instruct 405B
1 model
7
Highest Intelligence
Llama 3.1 Instruct 70B
1 model
7
Highest Intelligence
Llama 3.1 Instruct 8B
1 model
7
Highest Intelligence
Llama 3 Instruct 70B
1 model
5
Highest Intelligence
Llama 3 Instruct 8B
1 model
5
Highest Intelligence
Llama 2 Chat 13B
1 model
5
Highest Intelligence
Llama 2 Chat 70B
1 model
5
Highest Intelligence
Llama 2 Chat 7B
1 model
6
Highest Intelligence
Llama 65B
1 model
5
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Muse Wonder Full (Max) | Meta | 56 | - | 1M | - | - | Not available | - | |
| Muse Wonder (Max) | Meta | 52 | - | 1M | $2.9 | 181 | Not available | | |
| Muse Spark 1.3 (Max) | Meta | 48 | - | 1M | $0.8 | 134 | Not available | | |
| Muse Spark 1.3 (Xhigh) | Meta | 45 | - | 1M | $0.8 | 294 | Not available | | |
| Muse Spark 1.2 (Xhigh) | Meta | 40 | - | 1M | $0.8 | 369 | Not available | | |
| Muse Spark Open (Xhigh) | Meta | 39 | 816B 42B active at inference time | 1M | $0.8 | 131 |    +2 | ||
| Muse Spark 1.1 (Xhigh) | Meta | 34 | - | 1M | $0.8 | 194 | Not available | | |
| Muse Spark | Meta | 31 | - | 262k | - | - | Not available | - | |
| Muse Glimmer (High) | Meta | 17 | 30B | 131k | $0.2 | 132 |    | ||
| Llama 4 Maverick | Meta | 9 | 402B 17B active at inference time | 1M | $0.3 | 55 |    +3 | ||
| Llama 3.3 Instruct 70B | Meta | 8 | 70B | 128k | $0.7 | 93 |   +8 | ||
| Llama 3.1 Instruct 405B | Meta | 7 | 405B | 128k | - | - | - | ||
| Llama 3.1 Instruct 8B | Meta | 7 | 8B | 128k | $0.0 | 139 |  +2 | ||
| Llama 3.1 Instruct 70B | Meta | 7 | 70B | 128k | $0.6 | 33 | | ||
| Llama 4 Scout | Meta | 6 | 109B 17B active at inference time | 10M | $0.2 | 86 | +2 | ||
| Llama 3.2 Instruct 90B (Vision) | Meta | 6 | 90B | 128k | - | - | - | ||
| Llama 2 Chat 7B | Meta | 6 | 7B | 4k | $0.1 | - |  | ||
| Llama 3.2 Instruct 3B | Meta | 6 | 3B | 128k | - | - | - | ||
| Llama 3 Instruct 70B | Meta | 5 | 70B | 8k | $0.9 | - | | ||
| Llama 3.2 Instruct 11B (Vision) | Meta | 5 | 11B | 128k | $0.3 | 22 | | ||
| Llama 2 Chat 70B | Meta | 5 | 70B | 4k | - | - | - | ||
| Llama 2 Chat 13B | Meta | 5 | 13B | 4k | - | - | - | ||
| Llama 65B | Meta | 5 | 65B | 2k | - | - | - | ||
| Llama 3.2 Instruct 1B | Meta | 5 | 1B | 128k | - | - | - | ||
| Llama 3 Instruct 8B | Meta | 5 | 8B | 8k | $0.1 | - | |