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
Intelligence Index
Total 9 models
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 9 models
Lowest Price
Blended price (per 1M tokens)
Total 9 models
Databricks offers 9 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 Kimi K3.1 Pro (46), GLM-5.3 (max) (32), and GLM-5.3-Flash (28).
- For time per task, Kimi K3 (low) (7.5 min), Kimi K3.1 Pro (10.6 min), and GLM-5.3 (max) (13.5 min) finish an Intelligence Index task fastest on Databricks. Time per task varies significantly across models, with the slowest taking 2.3x longer than the quickest.
- For latency, GLM-5.2 (non-reasoning) (1.35s), Qwen3 Next 80B A3B (1.38s), and Kimi K3 (low) (5.60s) offer the lowest time to first answer token.
- For pricing, GLM-5.3-Flash ($0.10), DeepSeek V4.1 Flash (max) ($0.20), and Qwen3 Next 80B A3B ($0.26) offer the lowest blended prices per 1M tokens. Prices vary up to 9.0x across models.
- For context window size, Kimi K3.1 Pro (1M), GLM-5.3 (max) (1M), and GLM-5.3-Flash (1M) support the largest context windows on Databricks.
Intelligence
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
Pricing
Cost per Intelligence Index Task
Intelligence Index vs. Price
Speed
Average of the single-request and multi-turn agentic workloads measured
Time per Intelligence Index Task
Quality
Endpoint Accuracy Index
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate
Caching
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
Further Analysis | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Kimi K3.1 Pro | 46 | $3.29 | 12.7 | 75.68 | 5.0% | 1M | Open | |||
GLM-5.3 (max) | 32 | $4.92 | 17.3 | 57.58 | 0.0% | 1M | Open | |||
GLM-5.3-Flash | 28 | $0.58 | 19.4 | 33.36 | 1.6% | 1M | Open | |||
Kimi K3 (low) | 17 | $1.86 | 8.1 | 5.04 | 0.0% | 1M | Open | |||
Qwen3 Next 80B A3B | -- | -- | -- | 1.35 | 0.0% | 262k | Open | |||
DeepSeek V4.1 Flash (max) | -- | -- | -- | 30.04 | 0.0% | 1M | Open | |||
GLM-5.2 (non-reasoning) | -- | -- | -- | 1.70 | 0.0% | 1M | Open | |||
GLM-5.2 (max) | -- | -- | -- | 13.26 | 0.0% | 1M | Open | |||
Kimi K3 (max) | -- | -- | -- | 39.82 | 0.0% | 205k | Open | |||
Key definitions
Frequently Asked Questions
Common questions about Databricks
Databricks offers 9 models that we track: Kimi K3.1 Pro, GLM-5.3 (max), GLM-5.3-Flash, Kimi K3 (low), Qwen3 Next 80B A3B, DeepSeek V4.1 Flash (max), GLM-5.2 (non-reasoning), GLM-5.2 (max), and Kimi K3 (max).
The most intelligent model available on Databricks is Kimi K3.1 Pro with an Intelligence Index score of 46.
The model with the lowest time per task on Databricks is Kimi K3 (low) at 7.5 minutes per Intelligence Index task. Time per task is the output tokens per task divided by end-to-end output speed, so lower means a task finishes sooner.
The model with the lowest time to first answer token on Databricks is GLM-5.2 (non-reasoning) at 1.35s. Lower latency means faster initial response time.
The most affordable model on Databricks by blended price is GLM-5.3-Flash at $0.10 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Databricks vary up to 23.1x across models, from $0.10 per 1M tokens for GLM-5.3-Flash 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.
Yes, all 9 models on Databricks support JSON mode for structured output.
Yes, all 9 models on Databricks support function calling (tool use).
Yes, Databricks offers 7 reasoning models: Kimi K3.1 Pro, GLM-5.3 (max), GLM-5.3-Flash, Kimi K3 (low), DeepSeek V4.1 Flash (max), GLM-5.2 (max), and Kimi K3 (max). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 9 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), time per task (how quickly the model completes an Intelligence Index task), 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.