Skip to main content

Best OpenAI Models in 2026

All OpenAI models ranked by benchmark performance — GPT-5, GPT-4o, o1, o3, and more.

Unless noted otherwise, ranking surfaces on this page use BenchLM's provisional leaderboard lane rather than the stricter sourced-only verified leaderboard.

Bottom line: GPT-5.4 is OpenAI's strongest model — it leads on knowledge and holds top 3 overall. GPT-5.4 Pro adds premium reasoning at higher cost. GPT-5.3 Codex is the coding specialist.

According to BenchLM.ai, GPT-5.5 leads this ranking with a score of 91, followed by GPT-5.4 Pro (91) and GPT-5.4 (89). The top three are separated by just a few points — any of them would perform well for this use case.

The best open-weight option is GPT-OSS 120B (ranked #21 with a score of 34). Proprietary models hold a clear advantage in this category, though open-weight options may suffice for less demanding use cases.

This ranking is based on provisional overall weighted scores across BenchLM.ai's scoring formula tracked by BenchLM.ai. For detailed model profiles, click any model name below. To compare two specific models head-to-head, use the "vs #" links.

What changed

GPT-5.4 leads OpenAI's lineup with the highest overall score and best knowledge (98).

GPT-5.4 Pro premium tier with perfect multimodal and math scores.

GPT-5.3 Codex coding-focused with perfect math and multilingual.

How to choose

Full Rankings (25 models)

GPT-5.5
OpenAI·Proprietary·1M

91

prov. overall

GPT-5.4 Pro
OpenAI·Proprietary·1.05M

91

prov. overall

GPT-5.4
OpenAI·Proprietary·1.05M

89

prov. overall

4
GPT-5.3 Codex
OpenAI·Proprietary·400K

86

prov. overall

5
o1-preview
OpenAI·Proprietary·200K

83

prov. overall

6
GPT-5.2
OpenAI·Proprietary·400K

79

prov. overall

7
GPT-5.1
OpenAI·Proprietary·200K

78

prov. overall

8
GPT-5 (high)
OpenAI·Proprietary·128K

77

prov. overall

9
GPT-5.2-Codex
OpenAI·Proprietary·400K

76

prov. overall

10
GPT-5.1-Codex-Max
OpenAI·Proprietary·400K

75

prov. overall

11
GPT-5 (medium)
OpenAI·Proprietary·128K

70

prov. overall

12
GPT-4.1
OpenAI·Proprietary·1M

57

prov. overall

13
o1
OpenAI·Proprietary·200K

57

prov. overall

14
o3
OpenAI·Proprietary·200K

57

prov. overall

15
o3-pro
OpenAI·Proprietary·200K

57

prov. overall

16
o3-mini
OpenAI·Proprietary·200K

55

prov. overall

17
GPT-4o mini
OpenAI·Proprietary·128K

49

prov. overall

18
GPT-4.1 mini
OpenAI·Proprietary·1M

45

prov. overall

19
o4-mini (high)
OpenAI·Proprietary·200K

44

prov. overall

20
GPT-4o
OpenAI·Proprietary·128K

42

prov. overall

21
GPT-OSS 120B
OpenAI·Open Weight·128K

34

prov. overall

22
o1-pro
OpenAI·Proprietary·200K

29

prov. overall

23
GPT-4.1 nano
OpenAI·Proprietary·1M

27

prov. overall

24
GPT-4 Turbo
OpenAI·Proprietary·128K

25

prov. overall

25
GPT-OSS 20B
OpenAI·Open Weight·128K

17

prov. overall

These rankings update weekly

Get notified when models move. One email a week with what changed and why.

Free. No spam. Unsubscribe anytime.

Key Takeaways

The top model is GPT-5.5 by OpenAI with a provisional score of 91.

The best open-weight model is GPT-OSS 120B at position #21.

25 models are included in this ranking.

Score in Context

What these scores mean

Models are ranked by the same overall BenchLM score used across all leaderboards. Comparing within OpenAI's lineup helps identify which model fits your use case and budget.

Known limitations

This page only shows OpenAI models. Cross-provider comparison requires the overall or category-specific leaderboards. Newer models may have limited benchmark coverage initially.

Last updated: June 2, 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.