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)GLM-5.3-Flash
DeepSeek V4 Pro 0813 (max)
Kimi K3 (low)
Inkling (xhigh)Intelligence Index
Total 11 models
Fastest
GLM-5.2 (max)DeepSeek V4 Pro 0813 (max)GLM-5.2 (non-reasoning)Inkling (xhigh)GLM-5.3 (max)Output speed
Total 11 models
Lowest Price
DeepSeek V4 Flash 0731 (max)GLM-5.3-FlashDeepSeek V4.1 Flash (max)
Qwen3 Next 80B A3BInkling (xhigh)Blended price (per 1M tokens)
Total 11 models
Databricks offers 11 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) (32), GLM-5.3-Flash (28), and DeepSeek V4 Pro 0813 (max) (23).
- For output speed, the fastest models are GLM-5.2 (max) (335 t/s), DeepSeek V4 Pro 0813 (max) (289 t/s), and GLM-5.2 (non-reasoning) (257 t/s). Speed varies significantly across models, with a 74% difference between the fastest and slowest.
- For latency, Qwen3 Next 80B A3B (0.89s), GLM-5.2 (non-reasoning) (0.93s), and GLM-5.2 (max) (6.83s) offer the lowest time to first answer token.
- For pricing, DeepSeek V4 Flash 0731 (max) ($0.08), GLM-5.3-Flash ($0.10), and DeepSeek V4.1 Flash (max) ($0.20) 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
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
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 | 32 | $4.92 | 229 | 0.86 | 11.80 | 8.75 | |||
Inkling (xhigh) | 1M | Open | 12 | $1.38 | 250 | 1.29 | 11.29 | 8.00 | |||
GLM-5.3-Flash | 1M | Open | -- | -- | 143 | 0.97 | 18.46 | 13.99 | |||
Qwen3 Next 80B A3B | 262k | Open | -- | -- | 127 | 0.77 | 4.72 | -- | |||
Kimi K3 (low) | 1M | Open | -- | -- | 91 | 0.98 | 28.35 | 21.90 | |||
DeepSeek V4.1 Flash (max) | 1M | Open | -- | -- | 107 | 1.24 | 24.57 | 18.66 | |||
GLM-5.2 (non-reasoning) | 1M | Open | -- | -- | 225 | 0.88 | 3.11 | -- | |||
GLM-5.2 (max) | 1M | Open | -- | -- | 251 | 0.87 | 10.83 | 7.97 | |||
Kimi K3 (max) | 205k | Open | -- | -- | 103 | 0.95 | 25.11 | 19.33 | |||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | -- | -- | 134 | 1.82 | 20.54 | 14.97 | |||
Key definitions
Frequently Asked Questions
Common questions about Databricks
Databricks offers 11 models that we track: GLM-5.3 (max), GLM-5.3-Flash, DeepSeek V4 Pro 0813 (max), Kimi K3 (low), Inkling (xhigh), Qwen3 Next 80B A3B, DeepSeek V4.1 Flash (max), GLM-5.2 (non-reasoning), GLM-5.2 (max), Kimi K3 (max), and DeepSeek V4 Flash 0731 (max).
The most intelligent model available on Databricks is GLM-5.3 (max) with an Intelligence Index score of 32.
The fastest model on Databricks by output speed is GLM-5.2 (max) at 335.0 tokens per second.
The model with the lowest time to first answer token on Databricks is Qwen3 Next 80B A3B at 0.89s. Lower latency means faster initial response time.
The most affordable model on Databricks by blended price is DeepSeek V4 Flash 0731 (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 Flash 0731 (max) to $2.31 per 1M tokens for Kimi K3 (max).
Yes, Databricks offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
10 of 11 models on Databricks support JSON mode for structured output.
Yes, all 11 models on Databricks support function calling (tool use).
Yes, Databricks offers 9 reasoning models: GLM-5.3 (max), GLM-5.3-Flash, DeepSeek V4 Pro 0813 (max), Kimi K3 (low), Inkling (xhigh), DeepSeek V4.1 Flash (max), GLM-5.2 (max), Kimi K3 (max), and DeepSeek V4 Flash 0731 (max). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 11 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.