Skip to main content

Best Value LLM Overall in 2026 — Cost-Adjusted Rankings

This ranking answers the simplest question: which model gives you the most benchmark performance per dollar? It divides each model's overall weighted score (across all 8 categories) by its output token price. The leaders here are generalist value picks — strong across coding, reasoning, agentic, knowledge, and more, at prices that won't break your API budget. Start here if you need a single cost-effective model for mixed workloads.

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

Bottom line: Gemini 3.1 Flash-Lite offers the most all-around capability per dollar. GPT-4o mini is a strong OpenAI alternative. For budget-constrained mixed workloads, start here.

According to BenchLM.ai, DeepSeek V4 Flash (Max) leads this ranking with a score of 271.43, followed by DeepSeek V4 Flash (High) (253.57) and DeepSeek V4 Flash (210.71). There is a significant gap between the leading models and the rest of the field.

The best open-weight option is DeepSeek V4 Flash (Max) (ranked #1 with a score of 271.43). Open-weight models are highly competitive in this category — self-hosting is a viable alternative to proprietary APIs.

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

Gemini 3.1 Flash-Lite leads overall value — most benchmark performance per dollar across all categories.

GPT-4o mini best overall value in OpenAI's lineup.

GPT-4.1 nano strong value pick for reasoning-heavy mixed workloads.

How to choose

Full Rankings (66 models)

DeepSeek V4 Flash (Max)
DeepSeek·Open Weight·1M

271.43

Score/$

Score: 76 · $0.28/1M

DeepSeek V4 Flash (High)
DeepSeek·Open Weight·1M

253.57

Score/$

Score: 71 · $0.28/1M

DeepSeek V4 Flash
DeepSeek·Open Weight·1M

210.71

Score/$

Score: 59 · $0.28/1M

4
Grok 4.1 Fast
xAI·Proprietary·1M

140

Score/$

Score: 70 · $0.5/1M

5
DeepSeek V3.2
DeepSeek·Open Weight·128K

138.1

Score/$

Score: 58 · $0.42/1M

6
GPT-4o mini
OpenAI·Proprietary·128K

83.33

Score/$

Score: 50 · $0.6/1M

7
GPT-4.1 nano
OpenAI·Proprietary·1M

67.5

Score/$

Score: 27 · $0.4/1M

8
MiniMax M2.7
MiniMax·Open Weight·200K

51.67

Score/$

Score: 62 · $1.2/1M

9
DeepSeek V3
DeepSeek·Open Weight·128K

32.73

Score/$

Score: 36 · $1.1/1M

10
Mistral Large 3
Mistral·Proprietary·128K

32.67

Score/$

Score: 49 · $1.5/1M

11
Gemini 3.1 Flash-Lite
Google·Proprietary·1M

32

Score/$

Score: 48 · $1.5/1M

12
DeepSeek V3.2 (Thinking)
DeepSeek·Open Weight·128K

28.31

Score/$

Score: 62 · $2.19/1M

13
GPT-4.1 mini
OpenAI·Proprietary·1M

28.13

Score/$

Score: 45 · $1.6/1M

14
Grok Code Fast 1
xAI·Proprietary·256K

26.67

Score/$

Score: 40 · $1.5/1M

15
GLM-5 (Reasoning)
Z.AI·Open Weight·200K

25.63

Score/$

Score: 82 · $3.2/1M

16
Kimi K2.5 (Reasoning)
Moonshot AI·Proprietary·128K

25.33

Score/$

Score: 76 · $3/1M

17
DeepSeek V4 Pro (Max)
DeepSeek·Open Weight·1M

25.29

Score/$

Score: 88 · $3.48/1M

18
DeepSeek V4 Pro (High)
DeepSeek·Open Weight·1M

24.14

Score/$

Score: 84 · $3.48/1M

19
Qwen3.5 397B (Reasoning)
Alibaba·Open Weight·128K

21.94

Score/$

Score: 79 · $3.6/1M

20
Gemini 3 Flash
Google·Proprietary·1M

21.67

Score/$

Score: 65 · $3/1M

21
Kimi K2.5
Moonshot AI·Open Weight·256K

21.33

Score/$

Score: 64 · $3/1M

22
Kimi K2.6
Moonshot AI·Open Weight·256K

21.25

Score/$

Score: 85 · $4/1M

23
GLM-5
Z.AI·Open Weight·200K

20.94

Score/$

Score: 67 · $3.2/1M

24
DeepSeek V4 Pro
DeepSeek·Open Weight·1M

20.11

Score/$

Score: 70 · $3.48/1M

25
Claude 3 Haiku
Anthropic·Proprietary·200K

19.2

Score/$

Score: 24 · $1.25/1M

26
GLM-5.1
Z.AI·Open Weight·203K

18.86

Score/$

Score: 83 · $4.4/1M

27
Qwen3.5 397B
Alibaba·Open Weight·128K

17.78

Score/$

Score: 64 · $3.6/1M

28
GLM-4.5-Air
Z.AI·Proprietary·128K

17.27

Score/$

Score: 19 · $1.1/1M

29
Kimi K2
Moonshot AI·Proprietary·128K

16.8

Score/$

Score: 42 · $2.5/1M

30
Gemini 2.5 Flash
Google·Proprietary·1M

15.2

Score/$

Score: 38 · $2.5/1M

31
DeepSeek-R1
DeepSeek·Open Weight·128K

15.07

Score/$

Score: 33 · $2.19/1M

32
o3-mini
OpenAI·Proprietary·200K

12.73

Score/$

Score: 56 · $4.4/1M

33
GLM-4.5
Z.AI·Proprietary·128K

12.27

Score/$

Score: 27 · $2.2/1M

34
Claude Haiku 4.5
Anthropic·Proprietary·200K

11.6

Score/$

Score: 58 · $5/1M

35
Grok 4.20
xAI·Proprietary·2M

10.83

Score/$

Score: 65 · $6/1M

36
GPT-5.1
OpenAI·Proprietary·200K

7.9

Score/$

Score: 79 · $10/1M

37
GPT-5 (high)
OpenAI·Proprietary·128K

7.8

Score/$

Score: 78 · $10/1M

38
Gemini 3.1 Pro
Google·Proprietary·1M

7.67

Score/$

Score: 92 · $12/1M

39
GPT-5.1-Codex-Max
OpenAI·Proprietary·400K

7.6

Score/$

Score: 76 · $10/1M

40
GPT-4.1
OpenAI·Proprietary·1M

7.25

Score/$

Score: 58 · $8/1M

41
o3
OpenAI·Proprietary·200K

7.25

Score/$

Score: 58 · $8/1M

42
Gemini 1.5 Pro
Google·Proprietary·2M

7.2

Score/$

Score: 36 · $5/1M

43
Gemini 3 Pro
Google·Proprietary·2M

6.75

Score/$

Score: 81 · $12/1M

44
Gemini 2.5 Pro
Google·Proprietary·1M

6.5

Score/$

Score: 65 · $10/1M

45
GPT-5.3 Codex
OpenAI·Proprietary·400K

6.21

Score/$

Score: 87 · $14/1M

46
GPT-5.4
OpenAI·Proprietary·1.05M

5.93

Score/$

Score: 89 · $15/1M

47
GPT-5.2
OpenAI·Proprietary·400K

5.79

Score/$

Score: 81 · $14/1M

48
Claude Sonnet 4.6
Anthropic·Proprietary·200K

5.53

Score/$

Score: 83 · $15/1M

49
GPT-5.2-Codex
OpenAI·Proprietary·400K

5.5

Score/$

Score: 77 · $14/1M

50
Claude Sonnet 4.5
Anthropic·Proprietary·200K

4.4

Score/$

Score: 66 · $15/1M

51
GPT-4o
OpenAI·Proprietary·128K

4.3

Score/$

Score: 43 · $10/1M

52
Claude Opus 4.7 (Adaptive)
Anthropic·Proprietary·1M

3.6

Score/$

Score: 90 · $25/1M

53
Claude Opus 4.6
Anthropic·Proprietary·1M

3.48

Score/$

Score: 87 · $25/1M

54
Claude 4 Sonnet
Anthropic·Proprietary·200K

3.4

Score/$

Score: 51 · $15/1M

55
Claude Opus 4.5
Anthropic·Proprietary·200K

3.08

Score/$

Score: 77 · $25/1M

56
GPT-5.5
OpenAI·Proprietary·1M

3.03

Score/$

Score: 91 · $30/1M

57
Claude 3.5 Sonnet
Anthropic·Proprietary·200K

2.73

Score/$

Score: 41 · $15/1M

58
o1-preview
OpenAI·Proprietary·200K

1.38

Score/$

Score: 83 · $60/1M

59
o1
OpenAI·Proprietary·200K

0.95

Score/$

Score: 57 · $60/1M

60
GPT-4 Turbo
OpenAI·Proprietary·128K

0.83

Score/$

Score: 25 · $30/1M

61
Claude Mythos Preview
Anthropic·Proprietary·1M

0.79

Score/$

Score: 99 · $125/1M

62
o3-pro
OpenAI·Proprietary·200K

0.73

Score/$

Score: 58 · $80/1M

63
Claude 4.1 Opus
Anthropic·Proprietary·200K

0.69

Score/$

Score: 52 · $75/1M

64
GPT-5.4 Pro
OpenAI·Proprietary·1.05M

0.51

Score/$

Score: 91 · $180/1M

65
Claude 3 Opus
Anthropic·Proprietary·200K

0.47

Score/$

Score: 35 · $75/1M

66
o1-pro
OpenAI·Proprietary·200K

0.05

Score/$

Score: 29 · $600/1M

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 best value model is DeepSeek V4 Flash (Max) by DeepSeek with a provisional Score/$ ratio of 271.43 (score: 76, output: $0.28/1M tokens).

The best open-weight model is DeepSeek V4 Flash (Max) at position #1.

66 models are included in this ranking.

Score in Context

What these scores mean

Value scores divide the weighted overall score by output token price (per 1M tokens). Higher means more capability per dollar. Models with no listed price are excluded.

Known limitations

Value rankings favor cheap models even if absolute performance is modest. A model scoring half as well at one-tenth the price wins on value — but may not meet your quality bar. Always check raw scores alongside value rankings.

Last updated: May 13, 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.