Google: Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview
Context: 1,048,576In: $2.00/1MOut: $12.00/1MUpdated 2026-08-05
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
Intelligence
46.5
Coding
68.8
Agentic
21.4
Metric profile
Trend over time
Intelligence
46.5
Coding
68.8
Agentic
21.4
Only 1 snapshot so far (data refreshes daily) — the trend line appears after the 2nd snapshot.
Classic evals (curated from model cards)
Google Gemini — manually maintained, may lag releases
MMLU-Pro
80.4%
GPQA Diamond
81.7%
HumanEval
94%
AIME 2025
41.7%
Design Arena (ELO by category)
| Category | ELO | Win rate | Rank |
|---|---|---|---|
| svg | 1334 | 68.8% | #2 |
| asciiart | 1308 | 63.7% | #4 |
| uicomponent | 1302 | 68.1% | #15 |
| 3d | 1288 | 59.5% | #22 |
| website | 1274 | 64.3% | #23 |
| codecategories | 1270 | 64.2% | #27 |
| dataviz | 1252 | 60.5% | #32 |
| gamedev | 1245 | 54.2% | #32 |
| godotgamedev | 1236 | 60% | #6 |
| agentichtmlslides | 1226 | 55.8% | #5 |
| agenticslides(html) | 1219 | 54.4% | #5 |
| htmlslides | 1203 | 51.9% | #11 |
| webapps | 1173 | 46.6% | #22 |
| mobileapps | 1151 | 45% | #24 |
| agenticgamedev | 1124 | 44.1% | #17 |
| agenticslides | 1112 | 33.8% | #8 |
| fullstack | 1110 | 43.1% | #20 |
| pptxslides | 1110 | 34.1% | #8 |
| python-pptxslides | 1109 | 31.9% | #17 |
| agenticslides(python-pptx) | 1107 | 33.9% | #8 |
| androidnative | 1081 | 41.6% | #28 |