Recommendation

Ranking data as of November 13, 2026

Best Value LLM Overall in 2026 — Cost-Adjusted Rankings

As of November 13, 2026, the top model among value LLM overall on the BenchLM leaderboard is Qwen3.7 Flash with a score of 363.3.

Qwen3.7 Flash

Alibaba · 1M

Score: 47.2 · $0.13/1M

Mercury 2.5

Inception · 260K

Score: 32.9 · $0.15/1M

MiMo-V2.6-Flash

Xiaomi · 1M

Score: 54.5 · $0.28/1M

Full Rankings (127 ranked)

1

Alibaba·Proprietary·1M

363.31

Score/$

Score: 47.2 · $0.13/1M

2

Inception·Proprietary·260K

219.27

Score/$

Score: 32.9 · $0.15/1M

3

MiMo-V2.6-Flash

Xiaomi·Open Weight·1M

194.75

Score/$

Score: 54.5 · $0.28/1M

4

StepFun·Open Weight·256K

140.73

Score/$

Score: 42.2 · $0.3/1M

5

Claude Haiku 5.5

Anthropic·Proprietary·1M

135.28

Score/$

Score: 67.6 · $0.5/1M

6

OpenAI·Proprietary·1.05M

122.26

Score/$

Score: 61.1 · $0.5/1M

7

DeepSeek·Open Weight·128K

118.6

Score/$

Score: 49.8 · $0.42/1M

8

Alibaba·Proprietary·1M

113.75

Score/$

Score: 45.5 · $0.4/1M

9

Meta·Proprietary·1M

111.66

Score/$

Score: 55.8 · $0.5/1M

10

MiniMax M3.1 Flash

MiniMax·Proprietary·1M

97.8

Score/$

Score: 58.7 · $0.6/1M

11

OpenAI·Proprietary·400K

92.23

Score/$

Score: 36.9 · $0.4/1M

12

xAI·Proprietary·128K

87.9

Score/$

Score: 44 · $0.5/1M

13

xAI·Proprietary·1M

72.18

Score/$

Score: 36.1 · $0.5/1M

14

Xiaomi·Open Weight·1M

65.8

Score/$

Score: 57.3 · $0.87/1M

15

Inkling 2 Small

Thinking Machines Lab·Proprietary·1M

57.84

Score/$

Score: 57.8 · $1/1M

16

DeepSeek V4.1 Flash 1017

DeepSeek·Open Weight·1M

53.73

Score/$

Score: 64.5 · $1.2/1M

17

OpenAI·Proprietary·1.05M

52.65

Score/$

Score: 63.2 · $1.2/1M

18

Upstage·Proprietary·128K

50.03

Score/$

Score: 30 · $0.6/1M

19

OpenAI·Proprietary·1M

49.87

Score/$

Score: 20 · $0.4/1M

20

Trinity-Large-Thinking

Arcee AI·Open Weight·512K

48.02

Score/$

Score: 43.2 · $0.9/1M

21

Inception·Proprietary·128K

43.52

Score/$

Score: 32.6 · $0.75/1M

22

Mistral Small 4

Mistral·Open Weight·256K

43.17

Score/$

Score: 25.9 · $0.6/1M

23

OpenAI·Proprietary·128K

41.4

Score/$

Score: 24.8 · $0.6/1M

24

MiniMax·Open Weight·1M

41.18

Score/$

Score: 49.4 · $1.2/1M

25

MiniMax·Proprietary·128K

41.08

Score/$

Score: 49.3 · $1.2/1M

26

MiniMax·Open Weight·200K

38.99

Score/$

Score: 46.8 · $1.2/1M

27

Celeris·Proprietary·128K

38.77

Score/$

Score: 27.1 · $0.7/1M

28

StepFun·Open Weight·256K

38.72

Score/$

Score: 44.5 · $1.15/1M

29

OpenAI·Proprietary·400K

36.95

Score/$

Score: 46.2 · $1.25/1M

30

Thinking Machines Lab·Open Weight·1M

34.64

Score/$

Score: 49.9 · $1.44/1M

31

LiquidAI·Open Weight·131K

34.43

Score/$

Score: 34.4 · $1/1M

32

Z.AI·Proprietary·128K

31.55

Score/$

Score: 34.7 · $1.1/1M

33

Gemini 3.1 Flash-Lite

Google·Proprietary·1M

31.08

Score/$

Score: 46.6 · $1.5/1M

34

DeepSeek·Open Weight·128K

28.66

Score/$

Score: 31.5 · $1.1/1M

35

Multiverse Computing·Proprietary·1M

27.25

Score/$

Score: 49.1 · $1.8/1M

36

Mistral Large 4

Mistral·Open Weight·1M

24.8

Score/$

Score: 52.1 · $2.1/1M

37

OpenAI·Proprietary·128K

23.99

Score/$

Score: 48 · $2/1M

38

Grok Code Fast 1

xAI·Proprietary·256K

22.53

Score/$

Score: 33.8 · $1.5/1M

39

Mistral Large 3

Mistral·Open Weight·128K

22.22

Score/$

Score: 33.3 · $1.5/1M

40

xAI·Proprietary·2M

22.11

Score/$

Score: 55.3 · $2.5/1M

41

xAI·Proprietary·1M

21.03

Score/$

Score: 52.6 · $2.5/1M

42

StepFun·Open Weight·1M

20.54

Score/$

Score: 55.5 · $2.7/1M

43

Alibaba·Proprietary·1M

20.44

Score/$

Score: 49.1 · $2.4/1M

44

Kimi K2.5 (Reasoning)

Moonshot AI·Open Weight·128K

18.88

Score/$

Score: 56.6 · $3/1M

45

Gemini 3.5 Flash-Lite

Google·Proprietary·1M

18.78

Score/$

Score: 47 · $2.5/1M

46

DeepSeek·Open Weight·128K

18.57

Score/$

Score: 40.7 · $2.19/1M

47

Google·Proprietary·1M

17.94

Score/$

Score: 53.8 · $3/1M

48

Gemini 3.7 Flash

Google·Proprietary·1M

17.58

Score/$

Score: 65.9 · $3.75/1M

49

Moonshot AI·Open Weight·256K

17.52

Score/$

Score: 52.6 · $3/1M

50

Gemini 3.8 Flash

Google·Proprietary·1M

17.19

Score/$

Score: 64.5 · $3.75/1M

51

Z.AI·Open Weight·200K

16.94

Score/$

Score: 54.2 · $3.2/1M

52

Gemini 2.5 Flash

Google·Proprietary·1M

16.71

Score/$

Score: 41.8 · $2.5/1M

53

Gemini 3.6 Flash

Google·Proprietary·1M

16.59

Score/$

Score: 62.2 · $3.75/1M

54

OpenAI·Proprietary·1.05M

15.93

Score/$

Score: 79.6 · $5/1M

55

DeepSeek V4 Pro 0813

DeepSeek·Open Weight·1M

15.73

Score/$

Score: 62.3 · $3.96/1M

56

OpenAI·Proprietary·1M

15.68

Score/$

Score: 25.1 · $1.6/1M

57

Meta·Proprietary·1M

15.32

Score/$

Score: 65.1 · $4.25/1M

58

Alibaba·Open Weight·128K

15.19

Score/$

Score: 54.7 · $3.6/1M

59

Mistral Medium 3

Mistral·Proprietary·128K

14.3

Score/$

Score: 28.6 · $2/1M

60

Moonshot AI·Open Weight·256K

14.16

Score/$

Score: 56.6 · $4/1M

61

Z.AI·Open Weight·1M

13.57

Score/$

Score: 59.7 · $4.4/1M

62

Moonshot AI·Open Weight·256K

13.42

Score/$

Score: 53.7 · $4/1M

63

Moonshot AI·Proprietary·128K

13.35

Score/$

Score: 33.4 · $2.5/1M

64

Z.AI·Proprietary·200K

13.19

Score/$

Score: 52.8 · $4/1M

65

Z.AI·Open Weight·203K

12.61

Score/$

Score: 55.5 · $4.4/1M

66

Z.AI·Proprietary·200K

12.22

Score/$

Score: 48.9 · $4/1M

67

OpenAI·Proprietary·400K

11.76

Score/$

Score: 52.9 · $4.5/1M

68

xAI·Proprietary·500K

11.04

Score/$

Score: 66.2 · $6/1M

69

Anthropic·Proprietary·200K

11.02

Score/$

Score: 13.8 · $1.25/1M

70

Gemini 4 Hydrogen

Google·Proprietary·1M

10.54

Score/$

Score: 79.1 · $7.5/1M

71

xAI·Proprietary·500K

10.45

Score/$

Score: 62.7 · $6/1M

72

Thinking Machines Lab·Open Weight·1M

10.31

Score/$

Score: 48.2 · $4.68/1M

73

Gemini 4 Carbon

Google·Proprietary·1M

8.92

Score/$

Score: 89.2 · $10/1M

74

OpenAI·Proprietary·200K

8.75

Score/$

Score: 38.5 · $4.4/1M

75

OpenAI·Proprietary·1.05M

8.46

Score/$

Score: 84.6 · $10/1M

76

Claude Sonnet 5.5

Anthropic·Proprietary·1M

8.31

Score/$

Score: 83.1 · $10/1M

77

Claude Haiku 4.5

Anthropic·Proprietary·200K

8.03

Score/$

Score: 40.1 · $5/1M

78

Google·Proprietary·1M

7.9

Score/$

Score: 79 · $10/1M

79

OpenAI·Proprietary·1.05M

7.74

Score/$

Score: 77.4 · $10/1M

80

Moonshot AI·Open Weight·1.05M

7.04

Score/$

Score: 70.4 · $10/1M

81

Gemini 3.5 Flash

Google·Proprietary·1M

6.89

Score/$

Score: 62 · $9/1M

82

Claude Sonnet 5

Anthropic·Proprietary·1M

6.38

Score/$

Score: 63.8 · $10/1M

83

OpenAI·Proprietary·200K

6

Score/$

Score: 48 · $8/1M

84

OpenAI·Proprietary·1.05M

5.66

Score/$

Score: 68 · $12/1M

85

OpenAI·Proprietary·200K

5.64

Score/$

Score: 56.4 · $10/1M

86

Google·Proprietary·2M

5.56

Score/$

Score: 27.8 · $5/1M

87

Google·Proprietary·1M

5.26

Score/$

Score: 63.1 · $12/1M

88

OpenAI·Proprietary·400K

5.09

Score/$

Score: 50.9 · $10/1M

89

Google·Proprietary·1M

4.88

Score/$

Score: 48.8 · $10/1M

90

Google·Proprietary·2M

4.86

Score/$

Score: 58.4 · $12/1M

91

Moonshot AI·Open Weight·1.05M

4.56

Score/$

Score: 68.4 · $15/1M

92

OpenAI·Proprietary·1M

4.53

Score/$

Score: 36.3 · $8/1M

93

OpenAI·Proprietary·400K

4.41

Score/$

Score: 61.7 · $14/1M

94

OpenAI·Proprietary·1.05M

4.36

Score/$

Score: 65.4 · $15/1M

95

Claude Opus 5.5

Anthropic·Proprietary·1M

4.33

Score/$

Score: 86.6 · $20/1M

96

OpenAI·Proprietary·400K

4.2

Score/$

Score: 58.9 · $14/1M

97

OpenAI·Proprietary·400K

3.98

Score/$

Score: 55.7 · $14/1M

98

Mistral Medium 3.5 128B

Mistral·Open Weight·256K

3.76

Score/$

Score: 28.2 · $7.5/1M

99

Claude Sonnet 4.6

Anthropic·Proprietary·200K

3.72

Score/$

Score: 55.8 · $15/1M

100

OpenAI·Proprietary·1.05M

3.62

Score/$

Score: 72.5 · $20/1M

101

Meta·Proprietary·1M

3.37

Score/$

Score: 67.4 · $20/1M

102

Claude Sonnet 4.5

Anthropic·Proprietary·200K

3.11

Score/$

Score: 46.7 · $15/1M

103

Anthropic·Proprietary·

3.04

Score/$

Score: 76.1 · $25/1M

104

Cohere·Open Weight·128K

2.86

Score/$

Score: 28.6 · $10/1M

105

Claude Opus 4.8

Anthropic·Proprietary·1M

2.7

Score/$

Score: 67.5 · $25/1M

106

Claude Opus 4.7 (Adaptive)

Anthropic·Proprietary·1M

2.66

Score/$

Score: 66.4 · $25/1M

107

OpenAI·Proprietary·128K

2.57

Score/$

Score: 25.7 · $10/1M

108

Claude 4 Sonnet

Anthropic·Proprietary·200K

2.55

Score/$

Score: 38.2 · $15/1M

109

Claude Opus 4.7

Anthropic·Proprietary·1M

2.52

Score/$

Score: 63.1 · $25/1M

110

Claude Opus 4.6

Anthropic·Proprietary·1M

2.48

Score/$

Score: 62 · $25/1M

111

Claude Fable 5.2

Anthropic·Proprietary·1M

2.34

Score/$

Score: 93.7 · $40/1M

112

OpenAI·Proprietary·1M

2.2

Score/$

Score: 66 · $30/1M

113

Claude Opus 4.5

Anthropic·Proprietary·200K

2.12

Score/$

Score: 53 · $25/1M

114

OpenAI·Proprietary·1.05M

1.71

Score/$

Score: 85.7 · $50/1M

115

Claude 3.5 Sonnet

Anthropic·Proprietary·200K

1.69

Score/$

Score: 25.3 · $15/1M

116

Claude Fable 5.1

Anthropic·Proprietary·1M

1.58

Score/$

Score: 79.2 · $50/1M

117

Anthropic·Proprietary·1M+

1.53

Score/$

Score: 76.3 · $50/1M

118

OpenAI·Proprietary·128K

0.71

Score/$

Score: 21.2 · $30/1M

119

OpenAI·Proprietary·200K

0.6

Score/$

Score: 35.8 · $60/1M

120

OpenAI·Proprietary·200K

0.59

Score/$

Score: 35.6 · $60/1M

121

OpenAI·Proprietary·200K

0.56

Score/$

Score: 44.8 · $80/1M

122

Claude 4.1 Opus

Anthropic·Proprietary·200K

0.54

Score/$

Score: 40.2 · $75/1M

123

OpenAI·Proprietary·1M

0.39

Score/$

Score: 71 · $180/1M

124

OpenAI·Proprietary·400K

0.39

Score/$

Score: 65.9 · $168/1M

125

OpenAI·Proprietary·1.05M

0.37

Score/$

Score: 67 · $180/1M

126

Anthropic·Proprietary·200K

0.37

Score/$

Score: 28.1 · $75/1M

127

OpenAI·Proprietary·200K

0.06

Score/$

Score: 37 · $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 363.31 (score: 47.2, output: $0.13/1M tokens).

The best open-weight model is MiMo-V2.6-Flash at position #3.

127 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 November 13, 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 363.31, followed by Mercury 2.5 (219.27) and MiMo-V2.6-Flash (194.75). 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 #3 with a score of 194.75). 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: November 13, 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 7,000+ subscribers.

One email each week. Unsubscribe anytime.