Gemini 4 Neon
Google's Gemini 4 Neon is a reasoning model for complex coding, document analysis, scientific problem solving, and multi-step tasks that use tools. It accepts text and images and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output, with up to 983,040 input tokens and 65,536 combined thinking and output tokens per response. Choose low, medium, high, or extra-high thinking; high is the default.
- Reasoning
- Vision
- Tool Calling
- Structured Output
Added Nov 19, 2026
Pricing
Auto routing · per 1M tokens- Input
- $3.00
- Output
- $15.00
- Cache read
- $0.15
Specifications
- Context window
- 983K
- Max output
- 65.5K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1512.9
Overall Rank
#3 / 426
Votes
5,555
Confidence Interval
1504.4 - 1521.4
Category Scores
Coding
#2 / 421
1,288 votes
1559.0
Math
#2 / 408
212 votes
1534.5
Longer Query
#3 / 404
2,348 votes
1522.2
Creative Writing
#5 / 424
1,204 votes
1501.6
Instruction Following
#3 / 426
1,918 votes
1517.7
Hard Prompts
#3 / 426
3,508 votes
1541.6
Additional Categories18
French
#1 / 305
183 votes
1557.5
Industry Mathematical
#1 / 405
247 votes
1553.1
Industry Life And Physical And Social Science
#2 / 424
827 votes
1535.5
Industry Medicine And Healthcare
#2 / 394
323 votes
1527.7
Non English
#2 / 426
3,701 votes
1510.6
Russian
#2 / 390
970 votes
1543.5
Exclude Ties
#3 / 426
4,231 votes
1535.1
Industry Software And It Services
#4 / 426
1,944 votes
1540.6
Multi Turn
#4 / 424
815 votes
1520.4
Expert
#5 / 374
423 votes
1544.7
Chinese
#6 / 399
426 votes
1564.9
Industry Writing And Literature And Language
#6 / 425
1,635 votes
1505.4
English
#9 / 426
1,843 votes
1504.4
Hard Prompts English
#9 / 424
1,217 votes
1521.6
Spanish
#9 / 307
179 votes
1491.0
Industry Entertainment And Sports And Media
#12 / 424
1,423 votes
1477.1
Industry Legal And Government
#14 / 397
424 votes
1501.8
Industry Business And Management And Financial Operations
#27 / 419
891 votes
1484.3
Published 2026-11-19 · Matched as Gemini 4 Neon (High) · CC BY 4.0
LMArena DatasetLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 21, 2026 | ||
FrontierMath v2 (Tiers 1–3) | 91.2% | #6 of 84 |
GPQA Diamond | 96.3% | #5 of 119 |
SimpleQA Verified | 75.2% | #6 of 84 |
FrontierMath v2 (Tier 4) | 97.6% | #5 of 68 |
OTIS Mock AIME 2024–2025 | 100.0% | #8 of 121 |
Chess Puzzles | 83.0% | #1 of 83 |
Mystery Game Puzzles | 85.0% | #3 of 80 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
Recommended | $3.00 | $15.00 | $0.15 | N/A | N/A |