Quality
#14/7546.5
Overall quality score
🇺🇸GoogleClosed sourceGoogle: Gemini 3.1 Pro Preview.
See how Google: Gemini 3.1 Pro Preview compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#21/75101 t/s
Output tokens per second
Input price
#60/75$2.00/1M
Per 1M tokens
Output price
#64/75$12.00/1M
Per 1M tokens
Context
#30/751M
Content read at once
Comparison summary
Google: Gemini 3.1 Pro Preview ranks #14 of 75 for overall quality and #21 for response speed in the current catalogue.
Its listed input price is $2.00/1M, output price is $12.00/1M, and it can work with up to 1M of context at once.
Its strongest areas in the current data are following instructions, long documents, coding.
Practical specifications
- Company
- Reasoning
- Yes
- Open weights
- No
- Input
- Text, Image, Audio, Video
- Output
- Text
- Context window
- 1M
Google: Gemini 3.1 Pro Preview technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Gemini 3.1 Pro Preview | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 46.5 | OpenRouter model benchmarks |
| Coding Index | coding | 68.8 | OpenRouter model benchmarks |
| Agentic Index | agentic | 21.4 | OpenRouter model benchmarks |
| GPQA | GPQA Diamond | 94.1 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 44.7 | OpenRouter model benchmarks |
| IFBench | Instruction following | 77.1 | OpenRouter model benchmarks |
| τ²-Bench Telecom | Agentic tasks | 95.6 | OpenRouter model benchmarks |
| AA-LCR | Long-context reasoning | 72.7 | OpenRouter model benchmarks |
| GDPval-AA | Economically valuable tasks | 23.1 | OpenRouter model benchmarks |
| CritPt | Research-level physics | 17.7 | OpenRouter model benchmarks |
| SciCode | Scientific coding | 58.9 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Agentic coding | 53.8 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | Factual knowledge | 55.2 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | Reliability | 50.1 | OpenRouter model benchmarks |
Quality benchmarks
See where Google: Gemini 3.1 Pro Preview stands.
The darker bar marks Google: Gemini 3.1 Pro Preview; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better