Meta benchmarks.
A lab-level profile for Meta, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.
Lab rank
#23
By available Arena average
Models tracked
21
0 open-weight models
Portfolio coverage
17%
Average matched benchmark signals
Fastest model
0.90s
Muse Spark 1.1
Lab profile
Portfolio shape, leaders, and model coverage.
The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.
Portfolio read
Meta has 21 tracked benchmark profiles.
The portfolio combines 21 proprietary models and 0 open-weight models. Its average available Arena rank is 208.1, with a best category rank of #6. Average profile coverage is 17%, so model-level gaps remain visible in the cards below.
Best Arena model
Muse Spark
Best category rank #6
Highest coverage
Muse Spark 1.1
56% matched signals
Fastest response
Muse Spark 1.1
0.90s first token
Category leaders
Best model by benchmark lens.
Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.
Value
Quality, price, latency, and speed
Muse Spark 1.1
value index
Coding
Code Arena, SWE-bench, and output speed
Muse Spark 1.1
coding index
Agents
Search, document, code, and latency
Llama 2 7b Chat
agent proxy
Reasoning
Text, document, vision, and mode signals
Muse Spark 1.1
reasoning proxy
Context
Document, search, and text proxy
Muse Spark 1.1
context proxy
Meta value ranking table
Models from this lab with both quality and commercial price matches.
Top 2 of 2
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #9 | 84value index | $2.00blended / 1M tokens | 0.90stime to first token | 129 tok/soutput speed | 90quality signal | ArenaArtificial Analysis | |
| #119 | 52value index | $0.100blended / 1M tokens | 1.24stime to first token | 113 tok/soutput speed | 25quality signal | ArenaArtificial Analysis |
Model portfolio
Meta model coverage map.
Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.
Muse Spark 1.1
muse-spark-1.1
Coverage
56%
Best Arena
#6
Text
Value
#9
value index
Coding
#18
coding index
Latency
0.90s
129 tok/s
Muse Spark
muse-spark
Coverage
33%
Best Arena
#6
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 4 Maverick 17b 128e Instruct
llama-4-maverick-17b-128e-instruct
Coverage
22%
Best Arena
#88
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 4 Scout 17b 16e Instruct
llama-4-scout-17b-16e-instruct
Coverage
22%
Best Arena
#95
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.2 Vision 90b Instruct
llama-3.2-vision-90b-instruct
Coverage
11%
Best Arena
#116
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.2 Vision 11b Instruct
llama-3.2-vision-11b-instruct
Coverage
11%
Best Arena
#127
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.1 405b Instruct Bf16
llama-3.1-405b-instruct-bf16
Coverage
11%
Best Arena
#203
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.1 405b Instruct Fp8
llama-3.1-405b-instruct-fp8
Coverage
11%
Best Arena
#205
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.3 70b Instruct
llama-3.3-70b-instruct
Coverage
11%
Best Arena
#223
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.1 70b Instruct
llama-3.1-70b-instruct
Coverage
11%
Best Arena
#249
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3 70b Instruct
llama-3-70b-instruct
Coverage
11%
Best Arena
#263
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3 8b Instruct
llama-3-8b-instruct
Coverage
11%
Best Arena
#294
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.1 8b Instruct
llama-3.1-8b-instruct
Coverage
11%
Best Arena
#301
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 2 70b Chat
llama-2-70b-chat
Coverage
11%
Best Arena
#325
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.2 3b Instruct
llama-3.2-3b-instruct
Coverage
11%
Best Arena
#327
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 2 13b Chat
llama-2-13b-chat
Coverage
11%
Best Arena
#340
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Codellama 34b Instruct
codellama-34b-instruct
Coverage
11%
Best Arena
#345
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Codellama 70b Instruct
codellama-70b-instruct
Coverage
11%
Best Arena
#352
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 3.2 1b Instruct
llama-3.2-1b-instruct
Coverage
11%
Best Arena
#356
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Llama 2 7b Chat
llama-2-7b-chat
Coverage
44%
Best Arena
#358
Text
Value
#119
value index
Coding
#110
coding index
Latency
1.24s
113 tok/s
Llama 13b
llama-13b
Coverage
11%
Best Arena
#373
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
