Gemini 3.6 Flash
Google's GA Flash model delivers near-Pro coding and agentic capability at Flash-tier speed and cost, with improved token efficiency over Gemini 3.5 Flash. It is optimized for multi-step orchestration, full-stack code refactoring, general reasoning, and multimodal workflows.
- Reasoning
- Vision
- Audio Input
- Video Input
- Native PDF input
- Tool Calling
- Structured Output
Added Jul 21, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.75
- Output
- $3.75
- Cache read
- $0.075
Specifications
- Context window
- 1M
- Max output
- 65.5K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1482.7
Overall Rank
#28 / 422
Votes
35,294
Confidence Interval
1478.3 - 1487.2
Category Scores
Coding
#43 / 417
10,124 votes
1518.1
Math
#18 / 405
1,702 votes
1500.9
Longer Query
#40 / 400
16,632 votes
1484.9
Creative Writing
#19 / 420
7,355 votes
1471.4
Instruction Following
#39 / 422
12,785 votes
1472.9
Hard Prompts
#33 / 422
23,566 votes
1501.1
Additional Categories22
French
#11 / 302
1,130 votes
1511.5
Russian
#22 / 386
4,075 votes
1493.4
Chinese
#23 / 396
2,573 votes
1533.0
Industry Entertainment And Sports And Media
#24 / 420
9,042 votes
1461.4
Industry Writing And Literature And Language
#25 / 421
9,610 votes
1474.3
Multi Turn
#26 / 420
5,736 votes
1489.8
Spanish
#26 / 304
930 votes
1474.8
German
#27 / 321
583 votes
1484.6
Exclude Ties
#28 / 422
26,405 votes
1494.9
Japanese
#28 / 288
611 votes
1475.2
Non English
#28 / 422
20,410 votes
1472.4
Korean
#32 / 289
629 votes
1440.0
English
#33 / 422
14,882 votes
1485.4
Industry Life And Physical And Social Science
#35 / 420
5,665 votes
1495.3
Industry Software And It Services
#35 / 422
14,170 votes
1511.2
Polish
#38 / 243
527 votes
1476.4
Industry Business And Management And Financial Operations
#40 / 415
6,689 votes
1473.8
Industry Legal And Government
#42 / 394
2,931 votes
1480.6
Industry Mathematical
#42 / 403
2,034 votes
1486.5
Hard Prompts English
#45 / 420
9,951 votes
1498.4
Expert
#47 / 372
4,029 votes
1498.8
Industry Medicine And Healthcare
#57 / 392
2,488 votes
1480.9
Published 2026-11-18 · Matched as Gemini 3.6 Flash (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 19, 2026 | ||
Epoch Capabilities Index | 155.2 | #41 of 113 |
FrontierMath v2 (Tiers 1–3) | 58.9% | #44 of 83 |
GPQA Diamond | 94.1% | #14 of 118 |
SimpleQA Verified | 66.2% | #17 of 83 |
FrontierMath v2 (Tier 4) | 22.0% | #47 of 67 |
OTIS Mock AIME 2024–2025 | 94.2% | #48 of 120 |
MirrorCode | 23.3% | #35 of 41 |
Chess Puzzles | 42.0% | #34 of 82 |
Mystery Game Puzzles | 30.0% | #36 of 79 |
Creative Writing v3 | 1602 | #43 of 91 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 55.8 | #19 of 125 |
UGI Willingness | 2.2 | #87 of 125 |
UGI Writing | 69.8 | #11 of 125 |
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 | ||||||
|---|---|---|---|---|---|---|
Recommended | $0.75 | $3.75 | $0.075 | $0.0417 | N/A | N/A |
| $0.75 | $3.75 | $0.075 | $0.0417 | N/A | N/A | |
| $0.75 | $3.75 | $0.075 | $0.0417 | N/A | N/A |