Gemini 3 Flash (Preview)
Google's Gemini 3 Flash preview model optimized for speed while maintaining high capability. Features sub-second response times with strong multimodal understanding and reasoning. Audio input costs $1.00 per million audio tokens.
- Reasoning
- Vision
- Audio Input
- Video Input
- Tool Calling
- Structured Output
Added Dec 17, 2025
Pricing
Auto routing · per 1M tokens- Input
- $0.50
- Output
- $3.00
- Cache read
- $0.05
Specifications
- Context window
- 1M
- Max output
- 65.5K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1473.0
Overall Rank
#46 / 421
Votes
31,126
Confidence Interval
1468.7 - 1477.4
Category Scores
Coding
#68 / 416
6,555 votes
1505.2
Math
#47 / 404
2,062 votes
1474.4
Longer Query
#55 / 399
8,413 votes
1476.0
Creative Writing
#32 / 419
4,779 votes
1456.3
Instruction Following
#57 / 421
8,464 votes
1457.4
Hard Prompts
#48 / 421
17,057 votes
1492.9
Additional Categories22
German
#13 / 320
571 votes
1499.0
Japanese
#18 / 288
336 votes
1489.3
Polish
#19 / 243
973 votes
1496.7
Spanish
#21 / 304
996 votes
1477.9
Korean
#25 / 289
578 votes
1447.8
Russian
#29 / 385
4,137 votes
1486.1
Industry Entertainment And Sports And Media
#33 / 419
5,685 votes
1453.9
Industry Legal And Government
#35 / 393
2,401 votes
1483.4
Exclude Ties
#36 / 421
22,103 votes
1485.5
French
#36 / 301
819 votes
1492.6
Non English
#37 / 421
18,718 votes
1464.3
Multi Turn
#38 / 419
5,439 votes
1481.9
Industry Writing And Literature And Language
#39 / 420
6,997 votes
1460.8
Chinese
#41 / 395
2,453 votes
1516.4
Industry Business And Management And Financial Operations
#46 / 414
5,744 votes
1468.2
Industry Life And Physical And Social Science
#48 / 419
5,032 votes
1487.2
Expert
#51 / 371
2,171 votes
1497.5
Hard Prompts English
#51 / 419
6,579 votes
1490.8
English
#52 / 421
12,408 votes
1476.3
Industry Medicine And Healthcare
#55 / 391
2,140 votes
1481.9
Industry Software And It Services
#61 / 421
10,600 votes
1500.7
Industry Mathematical
#66 / 402
1,514 votes
1469.1
Published 2026-11-11 · Matched as Gemini 3 Flash · 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 13, 2026 | ||
Epoch Capabilities Index | 152.3 | #54 of 115 |
FrontierMath v2 (Tiers 1–3) | 51.2% | #54 of 83 |
SWE-bench Verified | 75.4% | #11 of 28 |
GPQA Diamond | 89.4% | #47 of 119 |
SimpleQA Verified | 66.8% | #13 of 82 |
FrontierMath v2 (Tier 4) | 17.1% | #51 of 67 |
OTIS Mock AIME 2024–2025 | 95.6% | #39 of 121 |
Chess Puzzles | 40.0% | #38 of 82 |
Mystery Game Puzzles | 26.0% | #38 of 77 |
Sierra τ-bench tau2-bench data, MIT · Updated Aug 4, 2026 | ||
τ²-bench Overall | 83.5% | #4 of 6 |
Longform Writing | 55.7 | #64 of 97 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 49.5 | #44 of 149 |
UGI Willingness | 1.8 | #129 of 149 |
UGI Writing | 67.7 | #17 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)
 Recommended | $0.50 | $3.00 | $0.05 | N/A | N/A |
| $0.50 | $3.00 | $0.05 | N/A | N/A | |
| $0.50 | $3.00 | $0.05 | N/A | N/A |
