Follow model changes

Recommendation

Best Value LLM Overall in 2026 — Cost-Adjusted Rankings

As of October 1, 2026, the top model in best value llm overall on the BenchLM leaderboard is Qwen3.7 Flash with a score of 377.3.

Ranking data as of October 1, 2026

Qwen3.7 Flash

Alibaba · 1M

Score: 49.1 · $0.13/1M

MiMo-V2.6-Flash

Xiaomi · 1M

Score: 66.4 · $0.28/1M

Mercury 2.5

Inception · 260K

Score: 35.2 · $0.15/1M

Full Rankings (116 models)

1

Alibaba·Proprietary·1M

377.31

Score/$

Score: 49.1 · $0.13/1M

2

MiMo-V2.6-Flash

Xiaomi·Open Weight·1M

237

Score/$

Score: 66.4 · $0.28/1M

3

Inception·Proprietary·260K

234.53

Score/$

Score: 35.2 · $0.15/1M

4

Mistral·Open Weight·128K

192.7

Score/$

Score: 19.3 · $0.1/1M

5

StepFun·Open Weight·256K

142.2

Score/$

Score: 42.7 · $0.3/1M

6

Mistral·Open Weight·128K

136.4

Score/$

Score: 20.5 · $0.15/1M

7

OpenAI·Proprietary·1.05M

129.9

Score/$

Score: 65 · $0.5/1M

8

Ministral 3 14B

Mistral·Open Weight·128K

126.95

Score/$

Score: 25.4 · $0.2/1M

9

DeepSeek·Open Weight·128K

121.26

Score/$

Score: 50.9 · $0.42/1M

10

Alibaba·Proprietary·1M

112.68

Score/$

Score: 45.1 · $0.4/1M

11

OpenAI·Proprietary·400K

92.7

Score/$

Score: 37.1 · $0.4/1M

12

xAI·Proprietary·128K

88.26

Score/$

Score: 44.1 · $0.5/1M

13

Xiaomi·Open Weight·1M

86.77

Score/$

Score: 75.5 · $0.87/1M

14

xAI·Proprietary·1M

73.38

Score/$

Score: 36.7 · $0.5/1M

15

OpenAI·Proprietary·1M

66.05

Score/$

Score: 26.4 · $0.4/1M

16

Mistral Small 4

Mistral·Open Weight·256K

58.47

Score/$

Score: 35.1 · $0.6/1M

17

OpenAI·Proprietary·1.05M

55.17

Score/$

Score: 66.2 · $1.2/1M

18

DeepSeek V4.1 Flash

DeepSeek·Open Weight·1M

53.86

Score/$

Score: 64.6 · $1.2/1M

19

Upstage·Proprietary·128K

50.63

Score/$

Score: 30.4 · $0.6/1M

20

Inception·Proprietary·128K

47.76

Score/$

Score: 35.8 · $0.75/1M

21

MiniMax·Open Weight·1M

45.97

Score/$

Score: 55.2 · $1.2/1M

22

OpenAI·Proprietary·128K

45.95

Score/$

Score: 27.6 · $0.6/1M

23

MiniMax·Proprietary·128K

41.98

Score/$

Score: 50.4 · $1.2/1M

24

Celeris·Proprietary·128K

41.29

Score/$

Score: 28.9 · $0.7/1M

25

OpenAI·Proprietary·400K

41.15

Score/$

Score: 51.4 · $1.25/1M

26

MiniMax·Open Weight·200K

40.46

Score/$

Score: 48.6 · $1.2/1M

27

StepFun·Open Weight·256K

38.99

Score/$

Score: 44.8 · $1.15/1M

28

Trinity-Large-Thinking

Arcee AI·Open Weight·512K

38.73

Score/$

Score: 34.9 · $0.9/1M

29

Thinking Machines Lab·Open Weight·1M

38.26

Score/$

Score: 55.1 · $1.44/1M

30

Gemini 3.1 Flash-Lite

Google·Proprietary·1M

32.99

Score/$

Score: 49.5 · $1.5/1M

31

Z.AI·Proprietary·128K

32.09

Score/$

Score: 35.3 · $1.1/1M

32

DeepSeek·Open Weight·128K

29.62

Score/$

Score: 32.6 · $1.1/1M

33

Multiverse Computing·Proprietary·1M

27.68

Score/$

Score: 49.8 · $1.8/1M

34

StepFun·Pending·1M

26.06

Score/$

Score: 70.4 · $2.7/1M

35

xAI·Proprietary·2M

23.67

Score/$

Score: 59.2 · $2.5/1M

36

Grok Code Fast 1

xAI·Proprietary·256K

23.05

Score/$

Score: 34.6 · $1.5/1M

37

Mistral Large 3

Mistral·Proprietary·128K

22.42

Score/$

Score: 33.6 · $1.5/1M

38

OpenAI·Proprietary·128K

22.38

Score/$

Score: 44.8 · $2/1M

39

xAI·Proprietary·1M

22.13

Score/$

Score: 55.3 · $2.5/1M

40

Gemini 3.5 Flash-Lite

Google·Proprietary·1M

20.61

Score/$

Score: 51.5 · $2.5/1M

41

Alibaba·Proprietary·1M

20.6

Score/$

Score: 49.4 · $2.4/1M

42

DeepSeek·Open Weight·128K

19.79

Score/$

Score: 43.3 · $2.19/1M

43

Gemini 3.8 Flash

Google·Proprietary·1M

19.71

Score/$

Score: 73.9 · $3.75/1M

44

OpenAI·Proprietary·1M

19.45

Score/$

Score: 31.1 · $1.6/1M

45

Google·Proprietary·1M

18.76

Score/$

Score: 56.3 · $3/1M

46

Gemini 3.7 Flash

Google·Proprietary·1M

18.12

Score/$

Score: 67.9 · $3.75/1M

47

Moonshot AI·Open Weight·256K

17.88

Score/$

Score: 53.7 · $3/1M

48

Gemini 2.5 Flash

Google·Proprietary·1M

17.49

Score/$

Score: 43.7 · $2.5/1M

49

Gemini 3.6 Flash

Google·Proprietary·1M

17.37

Score/$

Score: 65.2 · $3.75/1M

50

Z.AI·Open Weight·200K

17.2

Score/$

Score: 55 · $3.2/1M

51

DeepSeek V4 Pro 0813

DeepSeek·Open Weight·1M

16.4

Score/$

Score: 65 · $3.96/1M

52

Meta·Proprietary·1M

15.46

Score/$

Score: 65.7 · $4.25/1M

53

Mistral Medium 3

Mistral·Proprietary·128K

15.06

Score/$

Score: 30.1 · $2/1M

54

Moonshot AI·Open Weight·256K

15.04

Score/$

Score: 60.2 · $4/1M

55

Z.AI·Open Weight·1M

14.35

Score/$

Score: 63.2 · $4.4/1M

56

Z.AI·Proprietary·200K

13.66

Score/$

Score: 54.7 · $4/1M

57

Moonshot AI·Open Weight·256K

13.65

Score/$

Score: 54.6 · $4/1M

58

Z.AI·Open Weight·203K

13.12

Score/$

Score: 57.7 · $4.4/1M

59

Z.AI·Proprietary·200K

12.62

Score/$

Score: 50.5 · $4/1M

60

Anthropic·Proprietary·200K

12.49

Score/$

Score: 15.6 · $1.25/1M

61

OpenAI·Proprietary·400K

12.36

Score/$

Score: 55.6 · $4.5/1M

62

Moonshot AI·Proprietary·128K

11.86

Score/$

Score: 29.6 · $2.5/1M

63

Thinking Machines Lab·Open Weight·1M

11.71

Score/$

Score: 54.8 · $4.68/1M

64

xAI·Proprietary·500K

11.56

Score/$

Score: 69.4 · $6/1M

65

xAI·Proprietary·500K

10.94

Score/$

Score: 65.6 · $6/1M

66

OpenAI·Proprietary·200K

9.28

Score/$

Score: 40.8 · $4.4/1M

67

Claude Haiku 4.5

Anthropic·Proprietary·200K

8.48

Score/$

Score: 42.4 · $5/1M

68

Claude Sonnet 5.5

Anthropic·Proprietary·1M

8.33

Score/$

Score: 83.3 · $10/1M

69

OpenAI·Proprietary·1.05M

7.92

Score/$

Score: 79.2 · $10/1M

70

OpenAI·Proprietary·1.05M

7.76

Score/$

Score: 77.6 · $10/1M

71

Google·Proprietary·

7.72

Score/$

Score: 77.2 · $10/1M

72

Gemini 3.5 Flash

Google·Proprietary·1M

7.1

Score/$

Score: 63.9 · $9/1M

73

Claude Sonnet 5

Anthropic·Proprietary·1M

6.74

Score/$

Score: 67.4 · $10/1M

74

OpenAI·Proprietary·1.05M

6.1

Score/$

Score: 73.2 · $12/1M

75

OpenAI·Proprietary·200K

5.97

Score/$

Score: 47.7 · $8/1M

76

OpenAI·Proprietary·200K

5.9

Score/$

Score: 59 · $10/1M

77

Google·Proprietary·2M

5.63

Score/$

Score: 28.2 · $5/1M

78

Google·Proprietary·1M

5.42

Score/$

Score: 65.1 · $12/1M

79

Google·Proprietary·2M

5.13

Score/$

Score: 61.6 · $12/1M

80

OpenAI·Proprietary·400K

5.1

Score/$

Score: 51 · $10/1M

81

Google·Proprietary·1M

5.1

Score/$

Score: 51 · $10/1M

82

OpenAI·Proprietary·1M

4.91

Score/$

Score: 39.3 · $8/1M

83

Mistral Medium 3.5 128B

Mistral·Open Weight·256K

4.82

Score/$

Score: 36.2 · $7.5/1M

84

Moonshot AI·Pending·1.05M

4.81

Score/$

Score: 72.1 · $15/1M

85

OpenAI·Proprietary·1.05M

4.59

Score/$

Score: 68.9 · $15/1M

86

OpenAI·Proprietary·400K

4.46

Score/$

Score: 62.5 · $14/1M

87

OpenAI·Proprietary·400K

4.42

Score/$

Score: 61.9 · $14/1M

88

Claude Opus 5.5

Anthropic·Proprietary·1M

4.38

Score/$

Score: 87.7 · $20/1M

89

OpenAI·Proprietary·400K

4.05

Score/$

Score: 56.7 · $14/1M

90

OpenAI·Proprietary·1.05M

3.95

Score/$

Score: 78.9 · $20/1M

91

Claude Sonnet 4.6

Anthropic·Proprietary·200K

3.79

Score/$

Score: 56.9 · $15/1M

92

Cohere·Open Weight·128K

3.66

Score/$

Score: 36.6 · $10/1M

93

Claude Sonnet 4.5

Anthropic·Proprietary·200K

3.28

Score/$

Score: 49.1 · $15/1M

94

Anthropic·Proprietary·

3.2

Score/$

Score: 79.9 · $25/1M

95

OpenAI·Proprietary·128K

3

Score/$

Score: 30 · $10/1M

96

Claude Opus 4.8

Anthropic·Proprietary·1M

2.83

Score/$

Score: 70.8 · $25/1M

97

Claude Opus 4.7 (Adaptive)

Anthropic·Proprietary·1M

2.79

Score/$

Score: 69.6 · $25/1M

98

Claude Opus 4.7

Anthropic·Proprietary·1M

2.63

Score/$

Score: 65.8 · $25/1M

99

Claude Opus 4.6

Anthropic·Proprietary·1M

2.57

Score/$

Score: 64.3 · $25/1M

100

Claude 4 Sonnet

Anthropic·Proprietary·200K

2.57

Score/$

Score: 38.6 · $15/1M

101

OpenAI·Proprietary·1M

2.31

Score/$

Score: 69.4 · $30/1M

102

Claude Opus 4.5

Anthropic·Proprietary·200K

2.23

Score/$

Score: 55.6 · $25/1M

103

Claude 3.5 Sonnet

Anthropic·Proprietary·200K

1.97

Score/$

Score: 29.6 · $15/1M

104

OpenAI·Proprietary·1.05M

1.77

Score/$

Score: 88.7 · $50/1M

105

Claude Fable 5.1

Anthropic·Proprietary·1M

1.66

Score/$

Score: 82.8 · $50/1M

106

Anthropic·Proprietary·1M+

1.59

Score/$

Score: 79.4 · $50/1M

107

OpenAI·Proprietary·128K

0.74

Score/$

Score: 22.3 · $30/1M

108

OpenAI·Proprietary·200K

0.67

Score/$

Score: 40.1 · $60/1M

109

OpenAI·Proprietary·200K

0.62

Score/$

Score: 37 · $60/1M

110

OpenAI·Proprietary·200K

0.6

Score/$

Score: 47.9 · $80/1M

111

Claude 4.1 Opus

Anthropic·Proprietary·200K

0.54

Score/$

Score: 40.9 · $75/1M

112

OpenAI·Proprietary·1M

0.41

Score/$

Score: 74.6 · $180/1M

113

OpenAI·Proprietary·400K

0.41

Score/$

Score: 68.2 · $168/1M

114

OpenAI·Proprietary·1.05M

0.39

Score/$

Score: 70.7 · $180/1M

115

Anthropic·Proprietary·200K

0.39

Score/$

Score: 29.3 · $75/1M

116

OpenAI·Proprietary·200K

0.06

Score/$

Score: 36 · $600/1M

How to choose

Category-specific value?Check category-specific value pages (coding, agentic, etc.)Best raw performance regardless of cost?See the overall leaderboard

Key Takeaways

The best value model is Qwen3.7 Flash by Alibaba with a provisional Score/$ ratio of 377.31 (score: 49.1, output: $0.13/1M tokens).

The best open-weight model is MiMo-V2.6-Flash at position #2.

116 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.

About this ranking

Ranking data as of October 1, 2026

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. A very cheap model with a modest overall score can rank high here, so read the score column next to the value column before you shortlist one 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.

Qwen3.7 Flash leads this ranking with a score of 377.31, followed by MiMo-V2.6-Flash (237) and Mercury 2.5 (234.53). There is a significant gap between the leading models and the rest of the field.

The best open-weight option is MiMo-V2.6-Flash (ranked #2 with a score of 237). Open-weight models are highly competitive in this category — self-hosting is a viable alternative to proprietary APIs.

This ranking uses provisional overall weighted scores from the active scoring formula. For detailed model profiles, click any model name above. To compare two specific models head-to-head, use the "vs #" links.

Explore More

Last updated: October 1, 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.