Gemini 3.5 Flash Thinking
Gemini 3.5 Flash with higher thinking enabled for harder reasoning, agentic coding, tool use, multimodal analysis, and long-context workflows. Audio input costs $3.00 per million audio tokens.
- Reasoning
- Vision
- Audio Input
- Video Input
Added May 19, 2026
Pricing
Auto routing · per 1M tokens- Input
- $1.50
- Output
- $9.00
- Cache read
- $0.15
Specifications
- Context window
- 1M
- Max output
- 65.5K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1478.4
Overall Rank
#32 / 421
Votes
47,588
Confidence Interval
1474.5 - 1482.3
Category Scores
Coding
#65 / 416
13,576 votes
1508.0
Math
#20 / 404
2,318 votes
1497.4
Longer Query
#42 / 399
22,261 votes
1483.1
Creative Writing
#25 / 419
9,258 votes
1465.3
Instruction Following
#47 / 421
16,996 votes
1465.4
Hard Prompts
#43 / 421
31,750 votes
1496.0
Additional Categories22
Polish
#9 / 243
808 votes
1504.6
Japanese
#21 / 288
691 votes
1481.8
Industry Writing And Literature And Language
#22 / 420
12,386 votes
1474.9
Russian
#25 / 385
5,373 votes
1491.3
Non English
#28 / 421
27,371 votes
1470.1
Spanish
#28 / 304
1,408 votes
1474.1
German
#29 / 320
764 votes
1483.9
Industry Entertainment And Sports And Media
#30 / 419
11,637 votes
1454.8
Exclude Ties
#32 / 421
36,010 votes
1488.2
French
#34 / 301
1,514 votes
1494.4
Korean
#35 / 289
896 votes
1439.5
Multi Turn
#42 / 419
8,005 votes
1479.7
Industry Life And Physical And Social Science
#43 / 419
7,847 votes
1489.5
Chinese
#45 / 395
3,478 votes
1514.2
Industry Legal And Government
#45 / 393
3,979 votes
1478.5
English
#47 / 421
20,215 votes
1478.2
Industry Business And Management And Financial Operations
#47 / 414
9,197 votes
1467.8
Industry Medicine And Healthcare
#47 / 391
3,479 votes
1485.8
Industry Mathematical
#48 / 402
2,782 votes
1482.8
Hard Prompts English
#55 / 419
13,563 votes
1490.1
Industry Software And It Services
#57 / 421
18,998 votes
1501.7
Expert
#59 / 371
5,369 votes
1491.3
Published 2026-11-11 · Matched as Gemini 3.5 Flash (High) · CC BY 4.0
LMArena DatasetLeaderboard results
These leaderboards tested Gemini 3.5 Flash, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 18, 2026 | ||
Epoch Capabilities Index | 155.3 | #42 of 116 |
FrontierMath v2 (Tiers 1–3) | 62.8% | #42 of 84 |
SWE-bench Verified | 79.3% | #2 of 28 |
GPQA Diamond | 92.8% | #24 of 120 |
SimpleQA Verified | 66.2% | #15 of 83 |
FrontierMath v2 (Tier 4) | 26.8% | #43 of 68 |
OTIS Mock AIME 2024–2025 | 95.6% | #41 of 122 |
Chess Puzzles | 45.0% | #30 of 83 |
Mystery Game Puzzles | 32.0% | #32 of 78 |
EQ-Bench 4 | 1077 | #27 of 31 |
Longform Writing | 71.8 | #36 of 97 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 55.4 | #21 of 149 |
UGI Willingness | 2.2 | #103 of 149 |
UGI Writing | 72.5 | #5 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 | ||||||
|---|---|---|---|---|---|---|
Recommended | $1.50 | $9.00 | $0.15 | $0.0833 | N/A | N/A |
| $1.50 | $9.00 | $0.15 | $0.0833 | N/A | N/A | |
| $1.50 | $9.00 | $0.15 | $0.0833 | N/A | N/A |