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.

According to BenchLM.ai, Gemini 3.1 Flash-Lite leads this ranking with a score of 140, followed by GPT-4.1 nano (110) and GPT-4o mini (90). There is a significant gap between the leading models and the rest of the field.

The best open-weight option is DeepSeek Coder 2.0 (ranked #5 with a score of 56.36). 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 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.

Gemini 3.1 Flash-Lite
GoogleProprietary1M

140

Score/$

Score: 56 · $0.4/1M

GPT-4.1 nano
OpenAIProprietary1M

110

Score/$

Score: 44 · $0.4/1M

GPT-4o mini
OpenAIProprietary128K

90

Score/$

Score: 54 · $0.6/1M

4
Gemini 2.5 Flash
GoogleProprietary1M

83.33

Score/$

Score: 50 · $0.6/1M

5
DeepSeek Coder 2.0
DeepSeekOpen Weight128K

56.36

Score/$

Score: 62 · $1.1/1M

6
GPT-5.4 nano
OpenAIProprietary400K

46.4

Score/$

Score: 58 · $1.25/1M

7
DeepSeek V3
DeepSeekOpen Weight128K

44.55

Score/$

Score: 49 · $1.1/1M

8
GPT-4.1 mini
OpenAIProprietary1M

35.63

Score/$

Score: 57 · $1.6/1M

9
Kimi K2.5
Moonshot AIOpen Weight128K

25.71

Score/$

Score: 72 · $2.8/1M

10
Gemini 3 Flash
GoogleProprietary1M

22.33

Score/$

Score: 67 · $3/1M

11
DeepSeek-R1
DeepSeekOpen Weight128K

20.55

Score/$

Score: 45 · $2.19/1M

12
Gemini 3.1 Pro
GoogleProprietary1M

17.4

Score/$

Score: 87 · $5/1M

13
Claude Haiku 4.5
AnthropicProprietary200K

15.75

Score/$

Score: 63 · $4/1M

14
o3-mini
OpenAIProprietary200K

14.77

Score/$

Score: 65 · $4.4/1M

15
GPT-5.4 mini
OpenAIProprietary400K

14.67

Score/$

Score: 66 · $4.5/1M

16
GPT-5.1
OpenAIProprietary200K

13

Score/$

Score: 78 · $6/1M

17
Gemini 2.5 Pro
GoogleProprietary1M

13

Score/$

Score: 65 · $5/1M

18
GPT-5.2
OpenAIProprietary400K

10.25

Score/$

Score: 82 · $8/1M

19
GPT-5.2-Codex
OpenAIProprietary400K

10.25

Score/$

Score: 82 · $8/1M

20
GPT-5.1-Codex-Max
OpenAIProprietary400K

10.13

Score/$

Score: 81 · $8/1M

21
Mistral Large 3
MistralProprietary128K

9.67

Score/$

Score: 58 · $6/1M

22
GPT-5.3 Codex
OpenAIProprietary400K

8.5

Score/$

Score: 85 · $10/1M

23
GPT-4.1
OpenAIProprietary1M

8

Score/$

Score: 64 · $8/1M

24
Grok 4.1
xAIProprietary1M

5.67

Score/$

Score: 85 · $15/1M

25
Claude Sonnet 4.6
AnthropicProprietary200K

5.6

Score/$

Score: 84 · $15/1M

26
GPT-5.4
OpenAIProprietary1.05M

5.47

Score/$

Score: 82 · $15/1M

27
GPT-4o
OpenAIProprietary128K

5

Score/$

Score: 50 · $10/1M

28
Claude Sonnet 4.5
AnthropicProprietary200K

4.53

Score/$

Score: 68 · $15/1M

29
o3
OpenAIProprietary200K

1.6

Score/$

Score: 64 · $40/1M

30
Claude Opus 4.6
AnthropicProprietary1M

1.13

Score/$

Score: 85 · $75/1M

31
o1
OpenAIProprietary200K

1.07

Score/$

Score: 64 · $60/1M

32
GPT-5.4 Pro
OpenAIProprietary1.05M

0.51

Score/$

Score: 92 · $180/1M

33
o1-pro
OpenAIProprietary200K

0.08

Score/$

Score: 45 · $600/1M

Key Takeaways

  • The best value model is Gemini 3.1 Flash-Lite by Google with a Score/$ ratio of 140 (score: 56, output: $0.4/1M tokens).
  • The best open-weight model in this ranking is DeepSeek Coder 2.0 at position #5.
  • 33 models are included in this ranking.
Last updated: April 3, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.