Meta: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Meta for your use-case.
Most Intelligent
UpdatedMuse Spark 1.3 (max)Muse Spark 1.3 (xhigh)Muse Spark 1.2 (xhigh)Intelligence index
Total 3 models
Fastest
Muse Spark 1.3 (xhigh)Muse Spark 1.2 (xhigh)Muse Spark 1.3 (max)Output speed
Total 3 models
Lowest Price
Muse Spark 1.3 (max)Muse Spark 1.3 (xhigh)Muse Spark 1.2 (xhigh)Blended price (per 1M tokens)
Total 3 models
Meta offers 3 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Meta are Muse Spark 1.3 (max) (48), Muse Spark 1.3 (xhigh) (45), and Muse Spark 1.2 (xhigh) (40).
- For output speed, the fastest models are Muse Spark 1.3 (xhigh) (206 t/s), Muse Spark 1.2 (xhigh) (205 t/s), and Muse Spark 1.3 (max) (201 t/s).
- For latency, Muse Spark 1.2 (xhigh) (23.77s), Muse Spark 1.3 (xhigh) (33.48s), and Muse Spark 1.3 (max) (35.80s) offer the lowest time to first answer token.
- For pricing, Muse Spark 1.3 (max) ($0.78), Muse Spark 1.3 (xhigh) ($0.78), and Muse Spark 1.2 (xhigh) ($0.78) offer the lowest blended prices per 1M tokens.
- For context window size, Muse Spark 1.3 (max) (1M), Muse Spark 1.3 (xhigh) (1M), and Muse Spark 1.2 (xhigh) (1M) support the largest context windows on Meta.
- Muse Spark 1.3 (max) provides the best balance of intelligence and cost-effectiveness. For the fastest output, Muse Spark 1.3 (xhigh) is the top choice.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic knowledge work, (Elo-500)/2000
Agentic real-world work tasks, (Elo-500)/2000
Agentic SaaS workflows
Agentic coding & terminal use
Coding
Reasoning & knowledge
Professional document reasoning, All-pass
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Instruction following
Agentic tool use
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Muse Spark 1.3 (max) | 1.05M | Proprietary | 48 | $1.60 | 197 | 26.12 | 38.82 | 10.16 | |||
Muse Spark 1.3 (xhigh) | 1.05M | Proprietary | 45 | $1.37 | 203 | 25.19 | 37.52 | 9.86 | |||
Muse Spark 1.2 (xhigh) | 1.05M | Proprietary | 40 | $0.97 | 193 | 14.52 | 27.48 | 10.37 | |||
Muse Spark 1.1 (xhigh) | 1.05M | Proprietary | 34 | $1.38 | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Meta
Meta offers 3 models that we track: Muse Spark 1.3 (max), Muse Spark 1.3 (xhigh), and Muse Spark 1.2 (xhigh).
The most intelligent model available on Meta is Muse Spark 1.3 (max) with an Intelligence Index score of 48.
The fastest model on Meta by output speed is Muse Spark 1.3 (xhigh) at 206.4 tokens per second.
The model with the lowest time to first answer token on Meta is Muse Spark 1.2 (xhigh) at 23.77s. Lower latency means faster initial response time.
The most affordable model on Meta by blended price is Muse Spark 1.3 (max) at $0.78 per 1M tokens (7:2:1 cache hit/input/output ratio).
Yes, Meta offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 3 models on Meta support JSON mode for structured output.
Yes, all 3 models on Meta support function calling (tool use).
Yes, Meta offers 3 reasoning models: Muse Spark 1.3 (max), Muse Spark 1.3 (xhigh), and Muse Spark 1.2 (xhigh). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Meta, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.