Databricks: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Databricks for your use-case.
(te)
Most Intelligent
GLM-5.3 (max)
Kimi K3 (max)GLM-5.3-Flash
DeepSeek V4.1 Flash (max)DeepSeek V4 Flash 0731 (max)Intelligence Index
Total 10 models
Fastest
GLM-5.2 (max)GLM-5.2 (non-reasoning)GLM-5.3 (max)
Inkling (xhigh)GLM-5.3-FlashOutput speed
Total 10 models
Lowest Price
DeepSeek V4.1 Flash (max)DeepSeek V4 Flash 0731 (max)GLM-5.3-Flash
Qwen3 Next 80B A3BInkling (xhigh)Blended price (per 1M tokens)
Total 10 models
Databricks offers 10 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 Databricks are GLM-5.3 (max) (45), Kimi K3 (max) (44), and GLM-5.3-Flash (42).
- For output speed, the fastest models are GLM-5.2 (max) (261 t/s), GLM-5.2 (non-reasoning) (220 t/s), and GLM-5.3 (max) (205 t/s).
- For latency, GLM-5.2 (non-reasoning) (0.81s), Qwen3 Next 80B A3B (1.00s), and GLM-5.2 (max) (8.48s) offer the lowest time to first answer token.
- For pricing, DeepSeek V4.1 Flash (max) ($0.08), DeepSeek V4 Flash 0731 (max) ($0.08), and GLM-5.3-Flash ($0.10) offer the lowest blended prices per 1M tokens. Prices vary up to 9.6x across models.
- For context window size, DeepSeek V4 Flash 0731 (max) (1M), GLM-5.3 (max) (1M), and GLM-5.3-Flash (1M) support the largest context windows on Databricks.
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, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic scientific research workflows in a terminal
Quantitative analysis on spreadsheets & documents
Kubernetes incident root-cause analysis
Visual reasoning
Medical long context 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
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
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) | 1M | Open | 45 | $2.73 | 205 | 0.88 | 13.05 | 9.74 | |||
Kimi K3 (max) | 205k | Open | 44 | $1.85 | 133 | 0.94 | 19.69 | 15.00 | |||
GLM-5.3-Flash | 1M | Open | 42 | $0.28 | 176 | 0.64 | 14.84 | 11.36 | |||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.34 | 106 | 1.68 | 25.18 | 18.80 | |||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 34 | $0.17 | 137 | 1.79 | 20.09 | 14.64 | |||
GLM-5.2 (max) | 1M | Open | 34 | $0.87 | 261 | 0.80 | 10.39 | 7.67 | |||
Kimi K3 (low) | 1M | Open | 30 | $0.88 | 93 | 1.20 | 28.19 | 21.60 | |||
Inkling (xhigh) | 1M | Open | 25 | $0.61 | 202 | 1.40 | 13.81 | 9.92 | |||
GLM-5.2 (non-reasoning) | 1M | Open | 22* | -- | 220 | 0.81 | 3.09 | -- | |||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 103 | 1.00 | 5.85 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Databricks
Databricks offers 10 models that we track: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, DeepSeek V4.1 Flash (max), DeepSeek V4 Flash 0731 (max), GLM-5.2 (max), Kimi K3 (low), Inkling (xhigh), GLM-5.2 (non-reasoning), and Qwen3 Next 80B A3B.
The most intelligent model available on Databricks is GLM-5.3 (max) with an Intelligence Index score of 45.
The fastest model on Databricks by output speed is GLM-5.2 (max) at 260.6 tokens per second.
The model with the lowest time to first answer token on Databricks is GLM-5.2 (non-reasoning) at 0.81s. Lower latency means faster initial response time.
The most affordable model on Databricks by blended price is DeepSeek V4.1 Flash (max) at $0.08 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Databricks vary up to 31x across models, from $0.08 per 1M tokens for DeepSeek V4.1 Flash (max) to $2.31 per 1M tokens for Kimi K3 (low).
Yes, Databricks offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
9 of 10 models on Databricks support JSON mode for structured output.
Yes, all 10 models on Databricks support function calling (tool use).
Yes, Databricks offers 8 reasoning models: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, DeepSeek V4.1 Flash (max), DeepSeek V4 Flash 0731 (max), GLM-5.2 (max), Kimi K3 (low), and Inkling (xhigh). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 10 models on Databricks 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 Databricks, 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.