Gemini 3 Pro
gemini-3-pro
Last refreshed 2026-05-11. Next refresh: weekly.
Gemini 3 Pro is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Decision context: Coding task fit, 2 tracked provider routes, and research from 2026-01-01.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 1M context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
Cheapest output
$5.00
GCP Vertex AI per 1M tokens
Provider routes
2
Tracked API hosts
Quality / dollar
Grade D
Ranked by benchmark score divided by cheapest output price
Freshness
2026-01-01
Researched 137d ago
Top use-case fit
Coding
Q/$ D1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Provider price ladder
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| GCP Vertex AI | $1.25 | $5.00 | Serverless |
| Replicate API | $2.00 | $12.00 | Serverless |
Benchmark peer barsfor Coding
Migration checks
About
Google DeepMind's most advanced reasoning Gemini model. Part of the Gemini 3 series with frontier-class intelligence, multimodal understanding, and 1M token context window.
Gemini 3 Pro has a 1M-token context window.
Gemini 3 Pro input tokens at $1.25/1M, output at $5/1M.
Capabilities
Benchmark Scores(5)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Pro | 42.5 | — | DAT-1778 |
| Massive Multi-discipline Multimodal Understanding | 81.0 | — | https://mmmu-benchmark.github.io/ |
| BFCL | 72.5 | v4 | https://gorilla.cs.berkeley.edu/leaderboard.html |
| MMLU PRO | 90.1 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| Chatbot Arena | 1486.0 | — | https://arena.ai/leaderboard |
