Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Google

Gemini 3.1 Pro (Preview Custom Tools)

Gemini 3.1 Pro preview variant tuned for better tool selection behavior in coding agents and multi-tool workflows. It reduces overuse of generic bash tools and improves function-calling reliability while retaining Gemini 3.1 Pro's multimodal reasoning and 1M-token context. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.

  • Reasoning
  • Vision
  • Audio Input
  • Video Input
  • Tool Calling
  • Structured Output

Added Feb 27, 2026

Pricing

Auto routing · per 1M tokens
Input
$2.00
Output
$12.00
Cache read
$0.20
Compare provider prices

Specifications

Context window
1M
Max output
65.5K

Benchmarks

Sourced from LMArena.

Arena Score

1486.7

Overall Rank

#20 / 421

Votes

132,296

Confidence Interval

1483.8 - 1489.7

Category Scores

Coding

#37 / 416

36,091 votes

1520.2

Math

#31 / 404

6,870 votes

1487.6

Longer Query

#18 / 399

58,264 votes

1498.7

Creative Writing

#12 / 419

24,670 votes

1481.9

Instruction Following

#24 / 421

45,258 votes

1479.5

Hard Prompts

#22 / 421

85,874 votes

1507.4

Additional Categories
22

Russian

#12 / 385

15,297 votes

1501.2

Industry Writing And Literature And Language

#14 / 420

34,033 votes

1482.2

Spanish

#14 / 303

4,264 votes

1481.8

Industry Entertainment And Sports And Media

#15 / 419

30,760 votes

1469.5

Japanese

#15 / 288

1,651 votes

1494.4

Multi Turn

#16 / 419

22,333 votes

1495.2

Industry Legal And Government

#17 / 393

10,831 votes

1498.2

Industry Medicine And Healthcare

#18 / 390

9,858 votes

1504.8

Korean

#18 / 289

2,257 votes

1456.3

Non English

#18 / 421

74,597 votes

1478.5

Exclude Ties

#19 / 421

99,598 votes

1501.2

German

#19 / 320

2,220 votes

1495.3

Industry Life And Physical And Social Science

#20 / 419

21,958 votes

1509.4

Polish

#20 / 244

2,546 votes

1496.1

French

#22 / 301

4,402 votes

1501.3

English

#24 / 421

57,691 votes

1490.1

Chinese

#26 / 395

9,117 votes

1527.9

Hard Prompts English

#26 / 419

38,315 votes

1506.9

Industry Software And It Services

#32 / 421

51,750 votes

1511.8

Expert

#33 / 371

13,535 votes

1508.4

Industry Business And Management And Financial Operations

#33 / 414

25,559 votes

1477.6

Industry Mathematical

#48 / 401

7,350 votes

1483.1

Published 2026-11-09 · Matched as Gemini 3.1 Pro Preview · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026

FrontierMath v2 (Tiers 1–3)

Tested as Gemini 3.1 Pro

59.6%

#42 of 83

SWE-bench Verified

75.6%

#10 of 28

GPQA Diamond

Tested as Gemini 3.1 Pro

94.4%

#9 of 119

SimpleQA Verified

Tested as Gemini 3.1 Pro

73.5%

#6 of 82

FrontierMath v2 (Tier 4)

Tested as Gemini 3.1 Pro

26.8%

#41 of 67

OTIS Mock AIME 2024–2025

Tested as Gemini 3.1 Pro

95.6%

#38 of 121

MirrorCode

Tested as Gemini 3.1 Pro

8.9%

#38 of 39

Chess Puzzles

Tested as Gemini 3.1 Pro

51.0%

#17 of 82

Mystery Game Puzzles

Tested as Gemini 3.1 Pro

34.0%

#28 of 77

Sierra τ-bench

tau2-bench data, MIT · Updated Aug 4, 2026

τ³-Banking

Tested as Gemini 3.1 Pro

26.0%

#14 of 18

EQ-Bench

EQ-Bench data, MIT · Updated Nov 13, 2026

EQ-Bench 4

Tested as Gemini 3.1 Pro

1132

#24 of 31

Creative Writing v3

Tested as Gemini 3.1 Pro

1491

#58 of 96

Longform Writing

Tested as Gemini 3.1 Pro

68.2

#44 of 97

EQ-Bench 3

Tested as Gemini 3.1 Pro

1527

#15 of 49

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

Tested as Gemini 3.1 Pro

50.7

#40 of 149

UGI Willingness

Tested as Gemini 3.1 Pro

1.8

#130 of 149

UGI Writing

Tested as Gemini 3.1 Pro

72.2

#6 of 149

Filtered and ranked to models on NanoGPT.

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Cache write /M
Auto
Auto
Recommended
$2.00$12.00$0.20$0.375N/AN/A
>200kN/AN/A$0.40N/A
Google AI Studio
Google AI Studio
US
$2.00$12.00$0.20$0.375N/AN/A
>200kN/AN/A$0.40N/A
Privacy:No training on prompts

Related text models

Compare Gemini 3.1 Pro (Preview Custom Tools) with similar models from the same provider or model family.

Gemini Pro Latest

google/gemini-pro-latest

Compatibility alias that routes to the newest version of Gemini Pro. Currently routes to Gemini 3.1 Pro Preview High.

Gemini 3.1 Pro (Preview High)

google/gemini-3.1-pro-preview-high

Gemini 3.1 Pro preview high-reasoning variant.

Gemini 3.1 Pro (Preview Low)

google/gemini-3.1-pro-preview-low

Gemini 3.1 Pro preview low-reasoning variant.

Gemini 3.1 Pro (Preview)

google/gemini-3.1-pro-preview

Gemini 3.1 Pro preview is built for tasks where simple answers are not enough. Stronger core reasoning for complex coding, math, and long-context workflows, with multimodal support and a reported 77.1% verified score on ARC-AGI-2. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.

Gemini 4 Carbon

google/gemini-4-carbon

Google's Gemini 4 Carbon is a reasoning model for complex coding, scientific and mathematical problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output. Responses support up to 32,768 combined thinking and output tokens, with low, medium, and high thinking levels; medium is the default.

Gemini 4 Argon

google/gemini-4-argon

Google's Gemini 4 Argon is a flagship reasoning model for complex software engineering, mathematical and scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDFs, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output; synchronous output is capped at 65,536 tokens.