Gemini 3.1 Pro
- Input
- $2.00/M tok
- Output
- $12/M tok
- Blended
- $4.50/M tok · 3:1
- Speed
- 120tok/s
- Context
- 1Mtokens
- Cost per task
- ~$5.1/taskest.
Still in preview (gemini-3.1-pro-preview); Google's latest Pro model as of Sept 2026.
Rankings
Coding
Mixed#56 / 137rank by quality51.8±5.4quality / 1004/7 benchmarks measuredWriting & chat
Mixed#25 / 162rank by quality72.6±3.4quality / 1005/5 benchmarks measuredVision
Verified#30 / 98rank by quality67.5±4.0quality / 1004/6 benchmarks measuredHard reasoning
Verified#41 / 218rank by quality70.2±3.7quality / 1003/4 benchmarks measuredAgents
Mixed#41 / 187rank by quality53.9±3.4quality / 1005/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedLab-reported
#4 of 2080.6%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #3Beam 1.0 501B A23B81.6%
- #4Gemini 3.1 Pro80.6%
- #5MiniMax-M380.5%
deepmind.google · 2026-02-19
SWE-bench Pro (Public)Lab-reported
#18 of 2354.2%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #17Inkling54.3%
- #18Gemini 3.1 Pro54.2%
- #18Gemini 3.5 Flash-Lite54.2%
deepmind.google · 2026-02-19
DeepSWE v1.1Estimated
~#37 of 46 (estimated)~55.4%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #36Nex-N2.5-Pro55.8%
- ~#37Gemini 3.1 ProEstimated55.4%
- #37Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#42 of 1014.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #41Qwen3.8 27B5.6%
- #42Gemini 3.1 Pro4.0%
- #43GPT-5.4 mini2.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#12 of 28 (estimated)~79.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #11Gemma 4 31B80.0%
- ~#12Gemini 3.1 ProEstimated79.3%
- #12gpt-oss-20b77.7%
No published score — estimated from related benchmarks
SciCodeVerified
#14 of 11858.7%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #13Muse Spark 1.358.8%
- #14Gemini 3.1 Pro58.7%
- #15Muse Spark Open58.4%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#21 of 26 (estimated)~39.3
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #20Kimi K341.4
- ~#21Gemini 3.1 ProEstimated39.3
- #21Qwen3.8 Max (0902)39.2
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#18 of 13977.1%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #17DeepSeek V4.1 Flash NVFP477.3%
- #18Gemini 3.1 Pro77.1%
- #19Muse Glimmer77.0%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Verified
#6 of 561480 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #6Claude Opus 51480
- #6Gemini 3.1 Pro1480
- #8Kimi K31477
lmarena.ai · 2026-09-24
Vision
MMMU-ProVerified
#9 of 8782.4%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #8Qwen3.8 Max (0902)82.8%
- #9Gemini 3.1 Pro82.4%
- #10Muse Spark 1.382.0%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#6 of 12 (estimated)~82.0%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #5MiniMax-M3.1-Flash82.5%
- ~#6Gemini 3.1 ProEstimated82.0%
- #6Nemotron 3.5 Super VL80.8%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#20 of 4717.8%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #19MiMo-V2.6-Pro19.2%
- #20Gemini 3.1 Pro17.8%
- #21Grok 4.617.2%
artificialanalysis.ai · 2026-09-24
Hard reasoning
Humanity's Last ExamVerified
#17 of 19847.0%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #16Gemini 3.8 Flash47.8%
- #17Gemini 3.1 Pro47.0%
- #18Kimi K346.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#7 of 34 (estimated)~94.4%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #6Muse Glimmer94.7%
- ~#7Gemini 3.1 ProEstimated94.4%
- #7Nova 2.0 Lite94.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#3 of 11995.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #3Gemini 3.1 Pro95.6%
- #3Qwen3.5 397B A17B95.6%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#10 of 15 (estimated)~73.2%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #9Gemini 3.5 Flash-Lite74.0%
- ~#10Gemini 3.1 ProEstimated73.2%
- #10Nex-N2.5-Mini71.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompLab-reported
#8 of 2185.9%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #7GPT-5.6 Terra87.5%
- #8Gemini 3.1 Pro85.9%
- #9Claude Sonnet 584.7%
deepmind.google · 2026-02-19
GDPval-AA (Elo)Verified
#54 of 91776 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #53Qwen3.5 397B A17B780
- #54Gemini 3.1 Pro776
- #55Qwen3.7 Plus756
artificialanalysis.ai · 2026-09-24