Gemini 3.1 Pro Preview (batch)
Google · released Feb 19, 2026
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...
Specification
- Context window
- 1.05M
- Max output
- 66K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
Intelligence
47.7
94th percentile
Coding
68.8
Coding Index
Agentic
23.0
Agentic Index
Output speed
128 t/s
Median across providers
Latency
22.82s
Time to first token
Cost per task
$0.53
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)95.6%
- GPQA Diamond94.1%
- AA-LCR (long context)79.0%
- IFBench77.1%
- SciCode58.9%
- Terminal-Bench Hard53.8%
- Humanity's Last Exam47.0%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 95.6% |
| GPQA Diamond | 94.1% |
| AA-LCR (long context) | 79.0% |
| IFBench | 77.1% |
| SciCode | 58.9% |
| Terminal-Bench Hard | 53.8% |
| Humanity's Last Exam | 47.0% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Gemini 3.6 FlashGoogle51.6
- Gemini 3.1 Pro Preview (batch)Google47.7
- Gemini 3.1 Pro PreviewGoogle47.7
- Qwen3.7 MaxQwen46.7
- GPT-5.3-CodexOpenAI45.5
- MiniMax M3MiniMax45.4
- V4 ProDeepSeek45.3
- Kimi K2.6Moonshot AI45.1
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Gemini 3.6 Flash | 51.6 |
| Gemini 3.1 Pro Preview (batch) | 47.7 |
| Gemini 3.1 Pro Preview | 47.7 |
| Qwen3.7 Max | 46.7 |
| GPT-5.3-Codex | 45.5 |
| MiniMax M3 | 45.4 |
| V4 Pro | 45.3 |
| Kimi K2.6 | 45.1 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $1
- Output / 1M tokens
- $6
- Cached input / 1M
- Not offered
- Blended 3:1
- $2.25
One task, estimated
$0.53
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,333
- Win rate
- 68.8%
- Strongest at
- SVG
- Tournaments
- 4,307
Elo by category
Dot position on a 1,100–1,350 scale · Elo has no meaningful zero
- 1,333
- 1,288
- 1,262
- 1,255
- 1,241
- 1,238
- 1,151
- 1,108
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| SVG | 1333 | 68.8% |
| 3D scenes | 1288 | 59.4% |
| UI components | 1262 | 55.7% |
| Websites | 1255 | 55.4% |
| Game development | 1241 | 54.0% |
| Data visualisation | 1238 | 53.3% |
| Mobile apps | 1151 | 45.0% |
| Full-stack apps | 1108 | 43.0% |