Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM

BenchLM recommendation

Best Value LLM Overall in 2026 — Cost-Adjusted Rankings

Data verified

As of August 15, 2026, the top model in best value llm overall on the BenchLM leaderboard is Ministral 3 3B (Reasoning) with a score of 398.6.

Last verified: August 15, 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. 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.

Ministral 3 3B (Reasoning) leads this ranking with a score of 398.6, followed by Ministral 3 8B (Reasoning) (271.47) and Ministral 3 14B (Reasoning) (248.65). There is a significant gap between the leading models and the rest of the field.

The best open-weight option is Ministral 3 3B (Reasoning) (ranked #1 with a score of 398.6). 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 below. To compare two specific models head-to-head, use the "vs #" links.

1Open

Ministral 3 3B (Reasoning)

Mistral · 128K

398.6Score/$

Score: 39.9 · $0.1/1M

2Open

Ministral 3 8B (Reasoning)

Mistral · 128K

271.47Score/$

Score: 40.7 · $0.15/1M

3Open

Ministral 3 14B (Reasoning)

Mistral · 128K

248.65Score/$

Score: 49.7 · $0.2/1M

How to choose

Category-specific value?

Check category-specific value pages (coding, agentic, etc.)

Best raw performance regardless of cost?

See the overall leaderboard

Full Rankings (111 models)

1
Ministral 3 3B (Reasoning)
Mistral·Open Weight·128K

398.6

Score/$

Score: 39.9 · $0.1/1M

2
Ministral 3 8B (Reasoning)
Mistral·Open Weight·128K

271.47

Score/$

Score: 40.7 · $0.15/1M

3
Ministral 3 14B (Reasoning)
Mistral·Open Weight·128K

248.65

Score/$

Score: 49.7 · $0.2/1M

4
Step 3.5 Flash
StepFun·Open Weight·256K

180.97

Score/$

Score: 54.3 · $0.3/1M

5
Ministral 3 3B
Mistral·Open Weight·128K

178.2

Score/$

Score: 17.8 · $0.1/1M

6
Ministral 3 14B
Mistral·Open Weight·128K

169.45

Score/$

Score: 33.9 · $0.2/1M

7
Ministral 3 8B
Mistral·Open Weight·128K

135.27

Score/$

Score: 20.3 · $0.15/1M

8
DeepSeek V3.2
DeepSeek·Open Weight·128K

130.17

Score/$

Score: 54.7 · $0.42/1M

9
Qwen3.5 Flash
Alibaba·Proprietary·1M

118.18

Score/$

Score: 47.3 · $0.4/1M

10
GPT-5 nano
OpenAI·Proprietary·400K

116.23

Score/$

Score: 46.5 · $0.4/1M

11
GPT-4.1 nano
OpenAI·Proprietary·1M

105.5

Score/$

Score: 42.2 · $0.4/1M

12
Grok 4.1 Fast
xAI·Proprietary·1M

101.14

Score/$

Score: 50.6 · $0.5/1M

13
Mistral Small 4
Mistral·Open Weight·256K

77.18

Score/$

Score: 46.3 · $0.6/1M

14
DeepSeek V4 Pro 0813
DeepSeek·Proprietary·1M

70.3

Score/$

Score: 61.2 · $0.87/1M

15
Mercury 2
Inception·Proprietary·128K

64.19

Score/$

Score: 48.1 · $0.75/1M

16
GPT-4o mini
OpenAI·Proprietary·128K

62.03

Score/$

Score: 37.2 · $0.6/1M

17
MiniMax M3
MiniMax·Open Weight·1M

57.28

Score/$

Score: 68.7 · $1.2/1M

18
Trinity-Large-Preview
Arcee AI·Open Weight·512K

56.39

Score/$

Score: 56.4 · $1/1M

19
GPT-5.6 Luna
OpenAI·Proprietary·1.05M

56.08

Score/$

Score: 67.3 · $1.2/1M

20
GPT-5.4 nano
OpenAI·Proprietary·400K

53.27

Score/$

Score: 66.6 · $1.25/1M

21
Trinity-Large-Thinking
Arcee AI·Open Weight·512K

53.01

Score/$

Score: 47.7 · $0.9/1M

22
MiniMax M2.7
MiniMax·Open Weight·200K

52.55

Score/$

Score: 63.1 · $1.2/1M

23
MiniMax M2.5
MiniMax·Proprietary·128K

48.9

Score/$

Score: 58.7 · $1.2/1M

24
Inkling-Small
Thinking Machines Lab·Open Weight·1M

45.51

Score/$

Score: 65.5 · $1.44/1M

25
Step 3.7 Flash
StepFun·Open Weight·256K

44.27

Score/$

Score: 50.9 · $1.15/1M

26
GLM-4.5-Air
Z.AI·Proprietary·128K

42.72

Score/$

Score: 47 · $1.1/1M

27
DeepSeek V3
DeepSeek·Open Weight·128K

40.25

Score/$

Score: 44.3 · $1.1/1M

28
Gemini 3.1 Flash-Lite
Google·Proprietary·1M

33.67

Score/$

Score: 50.5 · $1.5/1M

29
Mistral Large 3
Mistral·Proprietary·128K

33.03

Score/$

Score: 49.5 · $1.5/1M

30
Aion-2.0
Aion Labs·Proprietary·128K

30.65

Score/$

Score: 49 · $1.6/1M

31
GPT-4.1 mini
OpenAI·Proprietary·1M

27.59

Score/$

Score: 44.1 · $1.6/1M

32
DeepSeek V3.2 (Thinking)
DeepSeek·Open Weight·128K

26.75

Score/$

Score: 58.6 · $2.19/1M

33
GLM-4.5
Z.AI·Proprietary·128K

26.37

Score/$

Score: 58 · $2.2/1M

34
Gemini 3.5 Flash-Lite
Google·Proprietary·1M

26.12

Score/$

Score: 65.3 · $2.5/1M

35
Grok 4.3
xAI·Proprietary·1M

25.58

Score/$

Score: 64 · $2.5/1M

36
Grok Code Fast 1
xAI·Proprietary·256K

25.19

Score/$

Score: 37.8 · $1.5/1M

37
DeepSeek-R1
DeepSeek·Open Weight·128K

23.26

Score/$

Score: 51 · $2.19/1M

38
Mistral Medium 3
Mistral·Proprietary·128K

21.69

Score/$

Score: 43.4 · $2/1M

39
GPT-5 mini
OpenAI·Proprietary·128K

21.54

Score/$

Score: 43.1 · $2/1M

40
GLM-5
Z.AI·Open Weight·200K

20.5

Score/$

Score: 65.6 · $3.2/1M

41
Kimi K2.5 (Reasoning)
Moonshot AI·Proprietary·128K

19.94

Score/$

Score: 59.8 · $3/1M

42
Gemini 3 Flash
Google·Proprietary·1M

19.91

Score/$

Score: 59.7 · $3/1M

43
Qwen3.5 Plus
Alibaba·Proprietary·1M

19.78

Score/$

Score: 47.5 · $2.4/1M

44
Kimi K2.5
Moonshot AI·Open Weight·256K

19.63

Score/$

Score: 58.9 · $3/1M

45
Gemini 2.5 Flash
Google·Proprietary·1M

18.98

Score/$

Score: 47.5 · $2.5/1M

46
GLM-5 (Reasoning)
Z.AI·Open Weight·200K

18.83

Score/$

Score: 60.3 · $3.2/1M

47
Qwen3.5 397B (Reasoning)
Alibaba·Open Weight·128K

16.66

Score/$

Score: 60 · $3.6/1M

48
Claude 3 Haiku
Anthropic·Proprietary·200K

16.54

Score/$

Score: 20.7 · $1.25/1M

49
GLM-5-Turbo
Z.AI·Proprietary·200K

16.52

Score/$

Score: 66.1 · $4/1M

50
Gemini 3.7 Flash
Google·Proprietary·1M

16.36

Score/$

Score: 61.4 · $3.75/1M

51
Qwen3.5 397B
Alibaba·Open Weight·128K

15.96

Score/$

Score: 57.5 · $3.6/1M

52
GLM-5V-Turbo
Z.AI·Proprietary·200K

15.57

Score/$

Score: 62.3 · $4/1M

53
GLM-5.1
Z.AI·Open Weight·203K

15.21

Score/$

Score: 66.9 · $4.4/1M

54
Kimi K2.6
Moonshot AI·Open Weight·256K

15.05

Score/$

Score: 60.2 · $4/1M

55
Muse Spark 1.2
Meta·Proprietary·1M

14.51

Score/$

Score: 61.7 · $4.25/1M

56
GLM-5.2
Z.AI·Open Weight·1M

14.4

Score/$

Score: 63.3 · $4.4/1M

57
Inkling
Thinking Machines Lab·Open Weight·1M

14.32

Score/$

Score: 67 · $4.68/1M

58
Kimi K2.7 Code
Moonshot AI·Open Weight·256K

13.59

Score/$

Score: 54.3 · $4/1M

59
GPT-5.4 mini
OpenAI·Proprietary·400K

12.64

Score/$

Score: 56.9 · $4.5/1M

60
Grok 4.5
xAI·Proprietary·500K

12.57

Score/$

Score: 75.4 · $6/1M

61
Claude Haiku 4.5
Anthropic·Proprietary·200K

11.41

Score/$

Score: 57.1 · $5/1M

62
o3-mini
OpenAI·Proprietary·200K

10.61

Score/$

Score: 46.7 · $4.4/1M

63
Grok 4.6
xAI·Proprietary·500K

10.57

Score/$

Score: 63.4 · $6/1M

64
Kimi K2
Moonshot AI·Proprietary·128K

10.53

Score/$

Score: 26.3 · $2.5/1M

65
Gemini 3.6 Flash
Google·Proprietary·1M

10.07

Score/$

Score: 75.5 · $7.5/1M

66
GPT-5.2 Instant
OpenAI·Proprietary·128K

9.91

Score/$

Score: 59.5 · $6/1M

67
Grok 4.20
xAI·Proprietary·2M

9.2

Score/$

Score: 55.2 · $6/1M

68
Gemini 3.5 Flash
Google·Proprietary·1M

7.19

Score/$

Score: 64.7 · $9/1M

69
Gemini 1.5 Pro
Google·Proprietary·2M

7

Score/$

Score: 35 · $5/1M

70
Claude Sonnet 5
Anthropic·Proprietary·1M

6.48

Score/$

Score: 64.8 · $10/1M

71
GPT-4.1
OpenAI·Proprietary·1M

6.36

Score/$

Score: 50.8 · $8/1M

72
GPT-5.6 Terra
OpenAI·Proprietary·1.05M

6.08

Score/$

Score: 72.9 · $12/1M

73
GPT-5 (high)
OpenAI·Proprietary·128K

5.91

Score/$

Score: 59.1 · $10/1M

74
o3
OpenAI·Proprietary·200K

5.88

Score/$

Score: 47 · $8/1M

75
Gemini 2.5 Pro
Google·Proprietary·1M

5.66

Score/$

Score: 56.6 · $10/1M

76
Gemini 3 Pro
Google·Proprietary·2M

5.61

Score/$

Score: 67.4 · $12/1M

77
GPT-5.1-Codex-Max
OpenAI·Proprietary·400K

5.49

Score/$

Score: 54.9 · $10/1M

78
Kimi K3
Moonshot AI·Pending·1.05M

5.37

Score/$

Score: 80.5 · $15/1M

79
GPT-5.1
OpenAI·Proprietary·200K

5.35

Score/$

Score: 53.5 · $10/1M

80
GPT-5.4
OpenAI·Proprietary·1.05M

4.89

Score/$

Score: 73.4 · $15/1M

81
Command A+
Cohere·Open Weight·128K

4.76

Score/$

Score: 47.6 · $10/1M

82
GPT-5.3 Codex
OpenAI·Proprietary·400K

4.71

Score/$

Score: 65.9 · $14/1M

83
Gemini 3.1 Pro
Google·Proprietary·1M

4.67

Score/$

Score: 56 · $12/1M

84
Claude Sonnet 4.6
Anthropic·Proprietary·200K

4.3

Score/$

Score: 64.5 · $15/1M

85
GPT-5.3 Instant
OpenAI·Proprietary·400K

4.24

Score/$

Score: 59.4 · $14/1M

86
GPT-5.2
OpenAI·Proprietary·400K

4.16

Score/$

Score: 58.2 · $14/1M

87
GPT-5.2-Codex
OpenAI·Proprietary·400K

4.16

Score/$

Score: 58.2 · $14/1M

88
GPT-4o
OpenAI·Proprietary·128K

4.08

Score/$

Score: 40.8 · $10/1M

89
Claude Sonnet 4.5
Anthropic·Proprietary·200K

3.61

Score/$

Score: 54.2 · $15/1M

90
Claude Opus 5
Anthropic·Proprietary·

3.32

Score/$

Score: 83.1 · $25/1M

91
Claude 3.5 Sonnet
Anthropic·Proprietary·200K

3.21

Score/$

Score: 48.1 · $15/1M

92
Claude Opus 4.8
Anthropic·Proprietary·1M

3.06

Score/$

Score: 76.6 · $25/1M

93
Claude Opus 4.7 (Adaptive)
Anthropic·Proprietary·1M

2.89

Score/$

Score: 72.1 · $25/1M

94
Claude Opus 4.7
Anthropic·Proprietary·1M

2.87

Score/$

Score: 71.9 · $25/1M

95
Claude 4 Sonnet
Anthropic·Proprietary·200K

2.8

Score/$

Score: 42 · $15/1M

96
GPT-5.6 Sol
OpenAI·Proprietary·1.05M

2.73

Score/$

Score: 82 · $30/1M

97
Claude Opus 4.6
Anthropic·Proprietary·1M

2.72

Score/$

Score: 68 · $25/1M

98
Claude Opus 4.5
Anthropic·Proprietary·200K

2.55

Score/$

Score: 63.6 · $25/1M

99
GPT-5.5
OpenAI·Proprietary·1M

2.45

Score/$

Score: 73.4 · $30/1M

100
Claude Mythos 5
Anthropic·Proprietary·1M+

1.66

Score/$

Score: 83.2 · $50/1M

101
Claude Fable 5
Anthropic·Proprietary·1M+

1.66

Score/$

Score: 83 · $50/1M

102
GPT-4 Turbo
OpenAI·Proprietary·128K

0.89

Score/$

Score: 26.7 · $30/1M

103
o1-preview
OpenAI·Proprietary·200K

0.81

Score/$

Score: 48.4 · $60/1M

104
o1
OpenAI·Proprietary·200K

0.8

Score/$

Score: 48.2 · $60/1M

105
Claude 4.1 Opus
Anthropic·Proprietary·200K

0.6

Score/$

Score: 45 · $75/1M

106
o3-pro
OpenAI·Proprietary·200K

0.59

Score/$

Score: 47.4 · $80/1M

107
Claude 3 Opus
Anthropic·Proprietary·200K

0.54

Score/$

Score: 40.4 · $75/1M

108
GPT-5.2 Pro
OpenAI·Proprietary·400K

0.45

Score/$

Score: 66.9 · $150/1M

109
GPT-5.5 Pro
OpenAI·Proprietary·1M

0.36

Score/$

Score: 64.2 · $180/1M

110
GPT-5.4 Pro
OpenAI·Proprietary·1.05M

0.34

Score/$

Score: 61.3 · $180/1M

111
o1-pro
OpenAI·Proprietary·200K

0.08

Score/$

Score: 46.1 · $600/1M

Key Takeaways

The best value model is Ministral 3 3B (Reasoning) by Mistral with a provisional Score/$ ratio of 398.6 (score: 39.9, output: $0.1/1M tokens).

The best open-weight model is Ministral 3 3B (Reasoning) at position #1.

111 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.

Explore More

Last updated: August 15, 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.