Gemini 3.1 Pro (Preview Low)
Gemini 3.1 Pro preview low-reasoning variant.
- Reasoning
- Vision
- Audio Input
- Tool Calling
- Structured Output
Added Feb 21, 2026
Pricing
Auto routing · per 1M tokens- Input
- $2.00
- Output
- $12.00
- Cache read
- $0.20
Specifications
- Context window
- 1M
- Max output
- 65.5K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1486.8
Overall Rank
#21 / 421
Votes
132,181
Confidence Interval
1483.9 - 1489.7
Category Scores
Coding
#36 / 416
36,054 votes
1520.4
Math
#30 / 404
6,862 votes
1487.8
Longer Query
#19 / 399
58,198 votes
1498.7
Creative Writing
#14 / 419
24,633 votes
1481.7
Instruction Following
#25 / 421
45,215 votes
1479.7
Hard Prompts
#22 / 421
85,808 votes
1507.5
Additional Categories22
Russian
#12 / 385
15,283 votes
1501.4
Industry Writing And Literature And Language
#15 / 420
33,991 votes
1482.1
Japanese
#15 / 288
1,650 votes
1494.7
Multi Turn
#15 / 419
22,314 votes
1495.4
Industry Entertainment And Sports And Media
#16 / 419
30,718 votes
1469.4
Spanish
#16 / 304
4,261 votes
1482.1
German
#19 / 320
2,230 votes
1494.7
Industry Legal And Government
#19 / 393
10,827 votes
1498.3
Industry Life And Physical And Social Science
#19 / 419
21,946 votes
1509.5
Industry Medicine And Healthcare
#19 / 391
9,860 votes
1504.6
Non English
#19 / 421
74,537 votes
1478.6
Exclude Ties
#20 / 421
99,520 votes
1501.3
Korean
#20 / 289
2,267 votes
1455.7
Polish
#20 / 243
2,531 votes
1496.3
French
#21 / 301
4,402 votes
1501.4
English
#26 / 421
57,636 votes
1490.1
Chinese
#27 / 395
9,096 votes
1527.8
Hard Prompts English
#27 / 419
38,288 votes
1506.8
Industry Software And It Services
#32 / 421
51,692 votes
1511.9
Industry Business And Management And Financial Operations
#33 / 414
25,546 votes
1477.8
Expert
#34 / 371
13,507 votes
1508.6
Industry Mathematical
#47 / 402
7,337 votes
1483.2
Published 2026-11-11 · Matched as Gemini 3.1 Pro Preview · CC BY 4.0
LMArena DatasetLeaderboard results
These leaderboards tested Gemini 3.1 Pro, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026 | ||
FrontierMath v2 (Tiers 1–3) | 59.6% | #42 of 83 |
SWE-bench Verified | 75.6% | #10 of 28 |
GPQA Diamond | 94.4% | #9 of 119 |
SimpleQA Verified | 73.5% | #6 of 82 |
FrontierMath v2 (Tier 4) | 26.8% | #41 of 67 |
OTIS Mock AIME 2024–2025 | 95.6% | #38 of 121 |
MirrorCode | 8.9% | #38 of 39 |
Chess Puzzles | 51.0% | #17 of 82 |
Mystery Game Puzzles | 34.0% | #28 of 77 |
Sierra τ-bench tau2-bench data, MIT · Updated Aug 4, 2026 | ||
τ³-Banking | 26.0% | #14 of 18 |
EQ-Bench 4 | 1132 | #24 of 31 |
Creative Writing v3 | 1491 | #58 of 96 |
Longform Writing | 68.2 | #44 of 97 |
EQ-Bench 3 | 1527 | #15 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 50.7 | #40 of 149 |
UGI Willingness | 1.8 | #130 of 149 |
UGI Writing | 72.2 | #6 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 | $2.00 | $12.00 | $0.20 | $0.375 | N/A | N/A |
| >200k | N/A | N/A | $0.40 | N/A | ||
| $2.00 | $12.00 | $0.20 | $0.375 | N/A | N/A | |
| >200k | N/A | N/A | $0.40 | N/A | ||
| $2.00 | $12.00 | $0.20 | $0.375 | N/A | N/A | |
| >200k | N/A | N/A | $0.40 | N/A |
