Modular: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Modular for your use-case.
Most Intelligent
GLM-5.3 (max)GLM-5.2 (max)
MiniMax-M3
Kimi K2.7 CodeGLM-5.2 (Non-reasoning)Intelligence index
Total 7 models
Fastest
Gemma 4 31B (NVFP4)Gemma 4 31B (Non-reasoning) (NVFP4)Kimi K2.7 CodeMiniMax-M3GLM-5.2 (max)Output speed
Total 7 models
Lowest Price
MiniMax-M3Gemma 4 31B (NVFP4)Gemma 4 31B (Non-reasoning) (NVFP4)GLM-5.3 (max)GLM-5.2 (max)Blended price (per 1M tokens)
Total 7 models
Modular offers 7 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 Modular are GLM-5.3 (max) (60), GLM-5.2 (max) (53), and MiniMax-M3 (45).
- For output speed, the fastest models are Gemma 4 31B (NVFP4) (239 t/s), Gemma 4 31B (Non-reasoning) (NVFP4) (231 t/s), and Kimi K2.7 Code (215 t/s). Speed varies significantly across models, with a 79% difference between the fastest and slowest.
- For latency, Gemma 4 31B (Non-reasoning) (NVFP4) (0.46s), Gemma 4 31B (NVFP4) (7.70s), and Kimi K2.7 Code (10.98s) offer the lowest time to first answer token.
- For pricing, MiniMax-M3 ($0.22), Gemma 4 31B (NVFP4) ($0.29), and Gemma 4 31B (Non-reasoning) (NVFP4) ($0.29) offer the lowest blended prices per 1M tokens. Prices vary up to 4.1x across models.
- For context window size, MiniMax-M3 (1M), Kimi K2.7 Code (262k), and Gemma 4 31B (NVFP4) (262k) support the largest context windows on Modular.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Instruction following
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 | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
GLM-5.3 (max) | 164k | Open | 60 | $0.69 | 43 | 10.22 | 68.94 | 46.98 | |||
GLM-5.2 (max) | 164k | Open | 53 | $0.42 | 133 | 18.78 | 37.56 | 15.02 | |||
MiniMax-M3 | 1M | Open | 45 | $0.13 | 179 | 1.80 | 15.75 | 11.16 | |||
Kimi K2.7 Code | 262k | Open | 43 | $0.57 | 215 | 0.63 | 13.30 | 10.35 | |||
GLM-5.2 (Non-reasoning) | 164k | Open | 35 | -- | 12 | 51.75 | 93.98 | -- | |||
Gemma 4 31B (NVFP4) | 262k | Open | 30 | -- | 239 | 0.43 | 9.80 | 7.27 | |||
Gemma 4 31B (Non-reasoning) (NVFP4) | 262k | Open | 22 | -- | 231 | 0.46 | 2.63 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Modular
Modular offers 7 models that we track: GLM-5.3 (max), GLM-5.2 (max), MiniMax-M3, Kimi K2.7 Code, GLM-5.2 (Non-reasoning), Gemma 4 31B (NVFP4), and Gemma 4 31B (Non-reasoning) (NVFP4).
The most intelligent model available on Modular is GLM-5.3 (max) with an Intelligence Index score of 60.
The fastest model on Modular by output speed is Gemma 4 31B (NVFP4) at 238.7 tokens per second.
The model with the lowest time to first answer token on Modular is Gemma 4 31B (Non-reasoning) (NVFP4) at 0.46s. Lower latency means faster initial response time.
The most affordable model on Modular by blended price is MiniMax-M3 at $0.22 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Modular vary up to 5x across models, from $0.22 per 1M tokens for MiniMax-M3 to $1.11 per 1M tokens for Kimi K2.7 Code.
Yes, Modular offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
6 of 7 models on Modular support JSON mode for structured output.
Yes, all 7 models on Modular support function calling (tool use).
Yes, Modular offers 5 reasoning models: GLM-5.3 (max), GLM-5.2 (max), MiniMax-M3, Kimi K2.7 Code, and Gemma 4 31B (NVFP4). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 7 models on Modular are open weight models.
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 Modular, 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.