Gemma 4 26B A4B

GoogleOpenApache 2.0

Gemma 4 26B A4B is a vision-language model from Google. It ranks 56 of 167 on LMArena’s overall vision board with 1260±6 from 23,922 votes. Its best category is Captioning (#4 of 34). License: Apache 2.0.

Key figures

LMArena · Overall1260±6#56 / 167 · Votes 23,922
OCR1268±7#56 / 123 · Votes 16,862
Diagrams1264±9#66 / 123 · Votes 6,239
Homework1293±10#44 / 118 · Votes 3,822
Captioning1297±70#4 / 34 · Votes 63
Entity recognition1191±36#42 / 51 · Votes 235
Creative writing1256±16#50 / 104 · Votes 1,495
Humor1272±19#36 / 93 · Votes 993
English1256±9#63 / 167 · Votes 9,635
Chinese1312±17#45 / 128 · Votes 1,609
Developer
Google
License
Apache 2.0
First seen (our snapshots)
2026-10-26

Who it suits

  • Overall #56 of 167: upper half.
  • Strongest category: Captioning (#4 of 34).
  • Open weights (Apache 2.0): you can self-host it.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
53MiMo-V2.6-Pro Xiaomi12631,754MIT+3
54Qwen3.5-397B-A17B Alibaba126232,657Apache 2.0+2
55Grok 4.20 Beta (Reasoning, 0309) xAI126226,796Proprietary+2
56Gemma 4 26B A4B Google126023,922Apache 2.0
57Grok 4.20 Multi-Agent Beta (0309) xAI125924,532Proprietary-1
58GPT-5.6 Luna (xHigh) OpenAI125711,055Proprietary-3
59MiMo-V2.6-Flash Xiaomi12563,618MIT-4

Alternatives · More from Google

#ModelScoreVotesLicense
7Gemini 3.8 Flash (High) Google13154,645Proprietary
8Gemini 3.7 Flash (High) Google13145,369Proprietary
13Gemini 3.5 Flash (High) Google130813,862Proprietary
14Gemini 3.5 Flash (Medium) Google130614,061Proprietary
16Gemini 3 Pro Google130513,623Proprietary

Alternatives · Top open-weight models

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129416,254MIT
34Kimi K2.6 Moonshot AI128216,368Modified MIT
38DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12784,100MIT
39Gemma 4 31B Google127640,219Apache 2.0
44Qwen3.8-27B Alibaba12697,614Apache 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 Gemma 4 26B A4B rank among vision models?

Overall rank 56 (1260); OCR rank 56 (1268); Diagrams rank 66 (1264); Homework rank 44 (1293); Captioning rank 4 (1297); Entity recognition rank 42 (1191); Creative writing rank 50 (1256); Humor rank 36 (1272); English rank 63 (1256); Chinese rank 45 (1312) (LMArena, data as of Oct 26, 2026).

How good is Gemma 4 26B A4B at OCR?

Gemma 4 26B A4B ranks 56 of 123 on LMArena’s OCR board with 1268 (16,862 votes).

Is Gemma 4 26B A4B better with Chinese or English prompts?

Chinese board: #45 of 128 (1312); English board: #63 of 167 (1256). The boards are computed separately, so compare ranks rather than scores.

Is Gemma 4 26B A4B open-weight?

LMArena lists its license as Apache 2.0, not proprietary; check the license text for commercial use.

How far is Gemma 4 26B A4B from #1?

#1 overall is Claude Fable 5 (High) (1325); Gemma 4 26B A4B has 1260, 65 points behind.

Sources

LMArena data published Oct 19, 2026.

Synced here Oct 26, 2026.

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