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, Gemini 3.1 Flash-Lite leads this ranking with a score of 127.5, followed by GPT-4o mini (75) and GPT-4.1 nano (70). There is a significant gap between the leading models and the rest of the field.

The best open-weight option is MiniMax M2.7 (ranked #5 with a score of 54.17). While proprietary models lead, open-weight options are within striking distance for teams willing to trade a few points of performance for full model control.

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 (37 models)

Gemini 3.1 Flash-Lite
Google·Proprietary·1M

127.5

Score/$

Score: 51 · $0.4/1M

GPT-4o mini
OpenAI·Proprietary·128K

75

Score/$

Score: 45 · $0.6/1M

GPT-4.1 nano
OpenAI·Proprietary·1M

70

Score/$

Score: 28 · $0.4/1M

4
Gemini 2.5 Flash
Google·Proprietary·1M

66.67

Score/$

Score: 40 · $0.6/1M

5
MiniMax M2.7
MiniMax·Open Weight·200K

54.17

Score/$

Score: 65 · $1.2/1M

6
DeepSeek Coder 2.0
DeepSeek·Open Weight·128K

48.18

Score/$

Score: 53 · $1.1/1M

7
DeepSeek V3
DeepSeek·Open Weight·128K

34.55

Score/$

Score: 38 · $1.1/1M

8
GPT-4.1 mini
OpenAI·Proprietary·1M

29.38

Score/$

Score: 47 · $1.6/1M

9
Kimi K2.5
Moonshot AI·Open Weight·128K

24.29

Score/$

Score: 68 · $2.8/1M

10
Gemini 3 Flash
Google·Proprietary·1M

22.33

Score/$

Score: 67 · $3/1M

11
GLM-5.1
Z.AI·Open Weight·203K

19.09

Score/$

Score: 84 · $4.4/1M

12
Gemini 3.1 Pro
Google·Proprietary·1M

18.8

Score/$

Score: 94 · $5/1M

13
DeepSeek-R1
DeepSeek·Open Weight·128K

16.44

Score/$

Score: 36 · $2.19/1M

14
GPT-5.4 mini
OpenAI·Proprietary·400K

16.22

Score/$

Score: 73 · $4.5/1M

15
Gemini 2.5 Pro
Google·Proprietary·1M

13.4

Score/$

Score: 67 · $5/1M

16
GPT-5.1
OpenAI·Proprietary·200K

13.33

Score/$

Score: 80 · $6/1M

17
o3-mini
OpenAI·Proprietary·200K

13.18

Score/$

Score: 58 · $4.4/1M

18
Grok 4.20
xAI·Proprietary·2M

12.83

Score/$

Score: 77 · $6/1M

19
Claude Haiku 4.5
Anthropic·Proprietary·200K

12

Score/$

Score: 60 · $5/1M

20
GPT-5.2
OpenAI·Proprietary·400K

10.38

Score/$

Score: 83 · $8/1M

21
GPT-5.2-Codex
OpenAI·Proprietary·400K

10

Score/$

Score: 80 · $8/1M

22
GPT-5.1-Codex-Max
OpenAI·Proprietary·400K

9.88

Score/$

Score: 79 · $8/1M

23
GPT-5.3 Codex
OpenAI·Proprietary·400K

8.9

Score/$

Score: 89 · $10/1M

24
Mistral Large 3
Mistral·Proprietary·128K

8.67

Score/$

Score: 52 · $6/1M

25
GPT-4.1
OpenAI·Proprietary·1M

7.5

Score/$

Score: 60 · $8/1M

26
GPT-5.4
OpenAI·Proprietary·1.05M

6.2

Score/$

Score: 93 · $15/1M

27
Claude Sonnet 4.6
Anthropic·Proprietary·200K

5.73

Score/$

Score: 86 · $15/1M

28
Grok 4.1
xAI·Proprietary·1M

5.33

Score/$

Score: 80 · $15/1M

29
Claude Sonnet 4.5
Anthropic·Proprietary·200K

4.53

Score/$

Score: 68 · $15/1M

30
GPT-4o
OpenAI·Proprietary·128K

4.1

Score/$

Score: 41 · $10/1M

31
Claude Opus 4.7
Anthropic·Proprietary·1M

3.76

Score/$

Score: 94 · $25/1M

32
Claude Opus 4.6
Anthropic·Proprietary·1M

3.68

Score/$

Score: 92 · $25/1M

33
o3
OpenAI·Proprietary·200K

1.5

Score/$

Score: 60 · $40/1M

34
o1
OpenAI·Proprietary·200K

0.98

Score/$

Score: 59 · $60/1M

35
Claude Mythos Preview
Anthropic·Proprietary·1M

0.79

Score/$

Score: 99 · $125/1M

36
GPT-5.4 Pro
OpenAI·Proprietary·1.05M

0.51

Score/$

Score: 92 · $180/1M

37
o1-pro
OpenAI·Proprietary·200K

0.05

Score/$

Score: 30 · $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 Gemini 3.1 Flash-Lite by Google with a provisional Score/$ ratio of 127.5 (score: 51, output: $0.4/1M tokens).

The best open-weight model is MiniMax M2.7 at position #5.

37 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: April 16, 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.