Gemini 3 Pro

GoogleProprietary

Gemini 3 Pro is a vision-language model from Google. It ranks 17 of 167 on LMArena’s overall vision board with 1305±7 from 13,547 votes. Its best category is Creative writing (#1 of 106). License: Proprietary.

Key figures

LMArena · Overall1305±7#17 / 167 · Votes 13,547
OCR1310±8#17 / 123 · Votes 8,264
Diagrams1302±12#33 / 123 · Votes 2,957
Homework1314±14#25 / 118 · Votes 1,763
Captioning1326±35#2 / 34 · Votes 218
Entity recognition1346±36#1 / 52 · Votes 248
Creative writing1342±19#1 / 106 · Votes 1,093
Humor1337±25#3 / 102 · Votes 609
English1292±10#23 / 167 · Votes 4,686
Chinese1370±17#12 / 135 · Votes 1,681
Developer
Google
License
Proprietary
First seen (our snapshots)
2026-10-26

Who it suits

  • Overall #17 of 167: upper half.
  • Strongest category: Creative writing (#1 of 106).
  • Proprietary; used through Google’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
14Muse Spark Meta13065,843Proprietary+1
15Gemini 3.5 Flash (Medium) Google130515,418Proprietary+0
16Muse Spark 1.2 (xHigh) Meta13051,930Proprietary+0
17Gemini 3 Pro Google130513,547Proprietary
18Muse Spark 1.3 (xHigh) Meta13017,522Proprietary-4
19GPT-5.4 (High) OpenAI130132,045Proprietary-4
20Gemini 3.6 Flash (High) Google129710,352Proprietary-8

Alternatives · More from Google

#ModelScoreVotesLicense
6Gemini 3.8 Flash (High) Google13177,624Proprietary
9Gemini 3.7 Flash (High) Google13136,840Proprietary
13Gemini 3.5 Flash (High) Google130815,325Proprietary
15Gemini 3.5 Flash (Medium) Google130515,418Proprietary
20Gemini 3.6 Flash (High) Google129710,352Proprietary

Alternatives · Top open-weight models

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129531,530MIT
34Kimi K2.6 Moonshot AI128216,265Modified MIT
36Gemma 4 31B Google127941,787Apache 2.0
37DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12794,247MIT
42Qwen3.8-27B Alibaba12709,632Apache 2.0

How to read these scores

  • If two scores differ by less than their ± intervals, the models are statistically close.
  • Each category board is computed independently; do not compare scores across categories.
  • Models with few votes move more; ranks of new entries may change.

FAQ

Where does Gemini 3 Pro rank among vision models?

Overall rank 17 (1305); OCR rank 17 (1310); Diagrams rank 33 (1302); Homework rank 25 (1314); Captioning rank 2 (1326); Entity recognition rank 1 (1346); Creative writing rank 1 (1342); Humor rank 3 (1337); English rank 23 (1292); Chinese rank 12 (1370) (LMArena, data as of Nov 14, 2026).

How good is Gemini 3 Pro at OCR?

Gemini 3 Pro ranks 17 of 123 on LMArena’s OCR board with 1310 (8,264 votes).

Is Gemini 3 Pro better with Chinese or English prompts?

Chinese board: #12 of 135 (1370); English board: #23 of 167 (1292). The boards are computed separately, so compare ranks rather than scores.

Is Gemini 3 Pro open-weight?

No. LMArena lists it as Proprietary; it is available through Google’s apps or API.

How far is Gemini 3 Pro from #1?

#1 overall is Claude Fable 5 (High) (1326); Gemini 3 Pro has 1305, 21 points behind.

Sources

LMArena data published Nov 9, 2026.

Synced here Nov 14, 2026.

Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.