Gemini 3.7 Flash
Google's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.
- Reasoning
- Vision
- Audio Input
- Video Input
- Native PDF input
- Tool Calling
- Structured Output
Added Aug 13, 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
1489.9
Overall Rank
#17 / 426
Votes
33,087
Confidence Interval
1485.2 - 1494.5
Category Scores
Coding
#39 / 421
8,892 votes
1520.5
Math
#20 / 408
1,677 votes
1501.4
Longer Query
#17 / 404
15,153 votes
1501.7
Creative Writing
#12 / 424
7,392 votes
1487.3
Instruction Following
#21 / 426
11,866 votes
1486.5
Hard Prompts
#23 / 426
21,497 votes
1510.5
Additional Categories22
Japanese
#4 / 288
539 votes
1519.5
Russian
#7 / 390
4,323 votes
1515.3
German
#8 / 321
510 votes
1510.3
Korean
#8 / 289
568 votes
1477.1
Chinese
#11 / 399
2,592 votes
1547.6
Polish
#11 / 243
544 votes
1503.9
Industry Writing And Literature And Language
#12 / 425
9,340 votes
1491.1
Non English
#14 / 426
20,000 votes
1485.2
Industry Entertainment And Sports And Media
#15 / 424
8,809 votes
1475.4
Exclude Ties
#17 / 426
24,875 votes
1504.5
Industry Life And Physical And Social Science
#18 / 424
5,513 votes
1513.4
Industry Medicine And Healthcare
#18 / 394
2,386 votes
1507.3
Industry Business And Management And Financial Operations
#20 / 419
5,969 votes
1486.2
Spanish
#20 / 307
1,061 votes
1479.4
Expert
#24 / 374
3,654 votes
1519.2
Multi Turn
#25 / 424
5,127 votes
1490.2
Industry Legal And Government
#26 / 397
2,736 votes
1496.9
Industry Mathematical
#30 / 405
1,997 votes
1496.6
French
#31 / 305
1,050 votes
1498.2
English
#32 / 426
13,085 votes
1486.4
Industry Software And It Services
#34 / 426
12,573 votes
1512.8
Hard Prompts English
#39 / 424
8,578 votes
1499.8
Published 2026-11-19 · Matched as Gemini 3.7 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 22, 2026 | ||
Epoch Capabilities Index | 158.4 | #25 of 114 |
FrontierMath v2 (Tiers 1–3) | 71.6% | #29 of 84 |
GPQA Diamond | 94.8% | #10 of 119 |
SimpleQA Verified | 69.2% | #15 of 84 |
FrontierMath v2 (Tier 4) | 36.6% | #30 of 68 |
OTIS Mock AIME 2024–2025 | 97.2% | #37 of 121 |
MirrorCode | 41.1% | #24 of 41 |
Chess Puzzles | 66.0% | #8 of 83 |
Mystery Game Puzzles | 37.0% | #25 of 80 |
Creative Writing v3 | 1720 | #32 of 91 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Nov 22, 2026 | ||
UGI Score | 47.0 | #49 of 125 |
UGI Willingness | 2.2 | #87 of 125 |
UGI Writing | 77.5 | #3 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 |