Gemini 3.1 Pro
A frontier model with strong performance in reasoning, achieving a 77.1% score on the ARC-AGI-2 benchmark.
Our editorial assessment as of Jun 4, 2026, based on the public sources listed below.
Overall rank
#5
Tier
S
Score
90.0
Main category
Reasoning
Strengths
- Leads on 13 of 16 benchmarks, including a 94.3% on GPQA Diamond for expert knowledge.
- Offers a large context window of up to 2 million tokens for analyzing extensive documents or videos.
- Strong multimodal capabilities, handling text, images, audio, and video simultaneously.
Considerations
- Pricing is higher than some cost-effective models.
- Performance on some tasks can be closely matched by competitors.
Price
API $2.00 / 1M tokens (input), $12.00 / 1M tokens (output)
Score breakdown
Performance
93.0
Reputation
92.0
Price
60.0
Recency
95.0
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
Sources
- Frontier AI Models 2026: GPT-5.3, Claude 4.6, G - TeamDay.aiAccessed: 2026-06-03
- Top 5 LLMs for March 2026 - AlphaCorpAccessed: 2026-06-03
- Introducing GPT-5.5 - OpenAI (Gemini 3.1 Pro comparison)Accessed: 2026-06-03
- Introducing the AI Frontier Model Tracker | DemandSphereAccessed: 2026-05-26
- AI Models in 2026: Which One Should You Actually Use? - GuruSupAccessed: 2026-05-26
- 22 AI Frontier Models Compared for 2026 - TeamAIAccessed: 2026-05-13
- Ranked: The Smartest AI Models of 2026 - Visual CapitalistAccessed: 2026-05-13
- AiZolo Top AI Models March 2026Accessed: 2026-04-20
- Design for Online - Best AI Models 2026Accessed: 2026-04-20