Skip to content
Model Pareto

Gemini 3.1 Pro

Google DeepMindProprietaryblog.google ↗
Compare with nearest rivalsCompare with…
Input
$2.00/M tok
Output
$12/M tok
Blended
$4.50/M tok · 3:1
Speed
120tok/s
Context
1Mtokens

Still in preview (gemini-3.1-pro-preview); Google's latest Pro model as of Sept 2026.

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

DeepSWE v1.1Estimated
~#22 of 31 (estimated)~59.8%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #21GLM-5.361.4%
  4. ~#22Gemini 3.1 ProEstimated59.8%
  5. #22Qwen3.8 Flash-Next58.7%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#6 of 20 (estimated)~85.6%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #5gpt-oss-120b87.8%
  4. ~#6Gemini 3.1 ProEstimated85.6%
  5. #6Gemma 4 31B80.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#11 of 15 (estimated)~46.6
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #10Grok 4.647.0
  4. ~#11Gemini 3.1 ProEstimated46.6
  5. #11Qwen3.8 Max (0902)43.3
No published score — estimated from related benchmarks

Writing & chat

LMArena Text, Non-English (Elo)Verified
#6 of 531480 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #4Gemini 3.8 FlashFew votes1483
  4. #6Gemini 3.1 Pro1480
  5. #7Kimi K31477
lmarena.ai · 2026-09-24
LMArena Text (Elo)Verified
#7 of 531487 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #6Kimi K31488
  4. #7Gemini 3.1 Pro1487
  5. #8GPT-5.51482
lmarena.ai · 2026-09-24

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Gemini 3.1 ProEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~82.0%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Gemini 3.1 ProEstimated82.0%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.7%
  1. #1Inkling97.1%
  2. ~#2Gemini 3.1 ProEstimated96.7%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#9 of 12 (estimated)~73.9%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #8Gemini 3.5 Flash-Lite74.0%
  4. ~#9Gemini 3.1 ProEstimated73.9%
  5. #9Nex-N2.5-Mini71.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Gemini 3.1 ProEstimated<47.5%
No published score — estimated from related benchmarks