What is the cheapest coding llm right now?

DeepSeek V4 Flash is the current #1 on this list. Rankings move when daily ingest updates SWE-bench, Elo, price, or latency.

How is this list ranked?

SWE-bench first, then price. For CI bots and repo agents that cannot burn Opus prices. Weights: SWE-bench 40%, Out $ 35%, Speed 15%, Code Elo 10%.

Is preference Elo the only score?

Preference Elo is a crowd vote from LMArena / Arena. People see two hidden answers and pick the one they like more. The model that wins more often gets a higher Elo. That means people preferred it — not that it passed a school test. It is not SWE-bench, not accuracy, and not a number we invent. This list uses a named Stack Engine mix — Elo is only one input when the job is “best chatbot,” not when the job is “cheapest coding agent.”

Why should I trust this over a tweet?

Every cell has a source and an as-of date. We noindex thin pages and we do not fill missing scores. Open the model or pair page and read the snapshot.

Search Intent · cheapest coding llm

Cheapest coding LLM in 2026

Repo agents ranked with SWE-bench first under a mid-tier budget. For CI bots that cannot burn Opus prices.

Weights:SWE-bench 40%Out $ 35%Speed 15%Code Elo 10%

Current #1 Ranked PickScore 76.2 / 100

DeepSeek V4 Flash

DeepSeek · Open weights

swe bench p74output price per m p83tokens per sec p81elo coding p54

SWE-bench: 71.2%Elo: 1,490

View full model fact sheet

Complete Ranked Category List

Models ranked by verified benchmark weights across SWE-bench and coding preference evaluations.

#1DeepSeek V4 Flash(DeepSeek)

Score 76.2

swe benchP74output price per mP83tokens per secP81elo codingP54

🏆 #1 Overall Leader in Category

#2Gemini 3.7 Flash(Google)

Score 71.1

swe benchP79output price per mP49tokens per secP99elo codingP75

Rank #2vs #1

#3MiniMax M2.5(MiniMax)

Score 70.8

swe benchP87output price per mP64tokens per secP45elo codingP68

Rank #3vs #1

#4GLM-5.3(Zhipu)

Score 69.8

swe benchP91output price per mP50tokens per secP45elo codingP91

Rank #4vs #1

#5Gemini 3 Flash(Google)

Score 67.0

swe benchP87output price per mP37tokens per secP96elo codingP48

Rank #5vs #1

#6Yi-Lightning(01.AI)

Score 66.6

swe benchP51output price per mP89tokens per secP76elo codingP37

Rank #6vs #1

#7OpenAI: o3 Mini(OpenAI)

Score 65.5

swe benchP96output price per mP31tokens per secP49elo codingP89

Rank #7vs #1

#8Gemini 2.0 Flash Thinking(Google)

Score 65.3

swe benchP58output price per mP77tokens per secP66elo codingP52

Rank #8vs #1

#9DeepSeek V4 Pro(DeepSeek)

Score 63.7

swe benchP76output price per mP65tokens per secP21elo codingP74

Rank #9vs #1

#10Gemini 3.6 Pro(Google)

Score 60.6

swe benchP85output price per mP28tokens per secP58elo codingP81

Rank #10vs #1

#11GPT-5.6 Luna(OpenAI)

Score 60.3

swe benchP45output price per mP73tokens per secP95elo codingP25

Rank #11vs #1

#12Gemini 3.6 Flash(Google)

Score 60.0

swe benchP71output price per mP34tokens per secP98elo codingP50

Rank #12vs #1

Frequently asked questions

Plain-English methodology and leaderboard answers

: DeepSeek V4 Flash is the current #1 on this list. Rankings move when daily ingest updates SWE-bench, Elo, price, or latency.

What is preference Elo? · How rankings update

Search Intent · cheapest coding llm

Cheapest coding LLM in 2026

Repo agents ranked with SWE-bench first under a mid-tier budget. For CI bots that cannot burn Opus prices.

Weights:SWE-bench 40%Out $ 35%Speed 15%Code Elo 10%

Current #1 Ranked PickScore 76.2 / 100

DeepSeek V4 Flash

DeepSeek · Open weights

swe bench p74output price per m p83tokens per sec p81elo coding p54

SWE-bench: 71.2%Elo: 1,490

View full model fact sheet

Complete Ranked Category List

Models ranked by verified benchmark weights across SWE-bench and coding preference evaluations.

#1DeepSeek V4 Flash(DeepSeek)

Score 76.2

swe benchP74output price per mP83tokens per secP81elo codingP54

🏆 #1 Overall Leader in Category

#2Gemini 3.7 Flash(Google)

Score 71.1

swe benchP79output price per mP49tokens per secP99elo codingP75

Rank #2vs #1

#3MiniMax M2.5(MiniMax)

Score 70.8

swe benchP87output price per mP64tokens per secP45elo codingP68

Rank #3vs #1

#4GLM-5.3(Zhipu)

Score 69.8

swe benchP91output price per mP50tokens per secP45elo codingP91

Rank #4vs #1

#5Gemini 3 Flash(Google)

Score 67.0

swe benchP87output price per mP37tokens per secP96elo codingP48

Rank #5vs #1

#6Yi-Lightning(01.AI)

Score 66.6

swe benchP51output price per mP89tokens per secP76elo codingP37

Rank #6vs #1

#7OpenAI: o3 Mini(OpenAI)

Score 65.5

swe benchP96output price per mP31tokens per secP49elo codingP89

Rank #7vs #1

#8Gemini 2.0 Flash Thinking(Google)

Score 65.3

swe benchP58output price per mP77tokens per secP66elo codingP52

Rank #8vs #1

#9DeepSeek V4 Pro(DeepSeek)

Score 63.7

swe benchP76output price per mP65tokens per secP21elo codingP74

Rank #9vs #1

#10Gemini 3.6 Pro(Google)

Score 60.6

swe benchP85output price per mP28tokens per secP58elo codingP81

Rank #10vs #1

#11GPT-5.6 Luna(OpenAI)

Score 60.3

swe benchP45output price per mP73tokens per secP95elo codingP25

Rank #11vs #1

#12Gemini 3.6 Flash(Google)

Score 60.0

swe benchP71output price per mP34tokens per secP98elo codingP50

Rank #12vs #1

Frequently asked questions

Plain-English methodology and leaderboard answers

: DeepSeek V4 Flash is the current #1 on this list. Rankings move when daily ingest updates SWE-bench, Elo, price, or latency.

What is preference Elo? · How rankings update