GPT-4o (2024-08-06)

OpenAIProprietary

GPT-4o (2024-08-06) is a vision-language model from OpenAI. It ranks 138 of 167 on LMArena’s overall vision board with 1064±13 from 3,376 votes. License: Proprietary.

Key figures

LMArena · Overall1064±13#138 / 167 · Votes 3,376
English1072±16#140 / 167 · Votes 1,744
Chinese1009±52#122 / 135 · Votes 186
Developer
OpenAI
License
Proprietary
First seen (our snapshots)
2026-10-26

No data: OCR, Diagrams, Homework, Captioning, Entity recognition, Creative writing, Humor.

Who it suits

  • Overall #138 of 167: lower half; consider it mainly for cost or deployment reasons.
  • Proprietary; used through OpenAI’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
135Gemini 1.5 Pro (001) Google108816,734Proprietary+24
136Molmo 2 8B Ai210821,187Apache 2.0+18
137GPT-4o mini (2024-07-18) OpenAI106617,341Proprietary+2
138GPT-4o (2024-08-06) OpenAI10643,376Proprietary
139GPT-4.1 nano (2025-04-14) OpenAI10631,211Proprietary-1
140Qwen-VL-Max (1119) Alibaba10571,422Proprietary-7
141Qwen2-VL-72B Alibaba10475,937Qwen-17

Alternatives · More from OpenAI

#ModelScoreVotesLicense
19GPT-5.4 (High) OpenAI130132,045Proprietary
22GPT-5.5 OpenAI129630,058Proprietary
25GPT-5.5 (High) OpenAI129528,348Proprietary
27GPT-5.4 OpenAI129222,608Proprietary
30GPT-6.1 Sol (Max) OpenAI12863,987Proprietary

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 GPT-4o (2024-08-06) rank among vision models?

Overall rank 138 (1064); English rank 140 (1072); Chinese rank 122 (1009) (LMArena, data as of Nov 14, 2026).

How good is GPT-4o (2024-08-06) at OCR?

GPT-4o (2024-08-06) is not on LMArena’s OCR board yet, so there is no score to cite.

Is GPT-4o (2024-08-06) better with Chinese or English prompts?

Chinese board: #122 of 135 (1009); English board: #140 of 167 (1072). The boards are computed separately, so compare ranks rather than scores.

Is GPT-4o (2024-08-06) open-weight?

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

How far is GPT-4o (2024-08-06) from #1?

#1 overall is Claude Fable 5 (High) (1326); GPT-4o (2024-08-06) has 1064, 262 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 –.