What is the best coding llm right now?

Claude Fable 5 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 with no budget cap. For when the patch quality matters more than the invoice. Weights: SWE-bench 55%, Code Elo 25%, Elo 20%.

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 · best coding llm

Best coding LLM in 2026 (SWE-bench)

Models ranked for repo work using dated SWE-bench snapshots, then price and speed. Not a single lab score.

Weights:SWE-bench 55%Code Elo 25%Elo 20%

Current #1 Ranked PickScore 98.8 / 100

Claude Fable 5

Anthropic · Closed flagship

SWE-bench: 80% (Top 1%)Code Elo: 1,622 (Top 1%)Elo: 1,616 (Top 2%)

SWE-bench: 80%Elo: 1,616

View full model fact sheet

Complete Ranked Category List

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

#1Claude Fable 5(Anthropic)

Score 98.8

SWE-bench: 80% (Top1%)Code Elo: 1,622 (Top1%)Elo: 1,616 (Top2%)

🏆 #1 Overall Leader in Category

#2Claude Opus 5(Anthropic)

Score 98.0

SWE-bench: 79.2% (Top2%)Code Elo: 1,618 (Top3%)Elo: 1,624 (Top1%)

Rank #2vs #1

#3Claude Opus 4.8(Anthropic)

Score 95.0

SWE-bench: 78.4% (Top5%)Code Elo: 1,604 (Top5%)Elo: 1,598 (Top5%)

Rank #3vs #1

#4GPT-5.6 Sol(OpenAI)

Score 94.2

SWE-bench: 77.6% (Top6%)Code Elo: 1,602 (Top7%)Elo: 1,608 (Top4%)

Rank #4vs #1

#5OpenAI o3-mini(OpenAI)

Score 92.7

SWE-bench: 78.5% (Top4%)Code Elo: 1,585 (Top11%)Elo: 1,560 (Top12%)

Rank #5vs #1

#6Claude Opus 4.5(Anthropic)

Score 90.4

SWE-bench: 76.8% (Top8%)Code Elo: 1,574 (Top12%)Elo: 1,568 (Top11%)

Rank #6vs #1

#7GLM-5.3(Zhipu)

Score 90.0

SWE-bench: 76.4% (Top9%)Code Elo: 1,586 (Top9%)Elo: 1,558 (Top14%)

Rank #7vs #1

#8Claude Opus 4.6(Anthropic)

Score 88.9

SWE-bench: 75.9% (Top11%)Code Elo: 1,570 (Top14%)Elo: 1,574 (Top8%)

Rank #8vs #1

#9Gemini 3.6 Pro(Google)

Score 85.5

SWE-bench: 74.6% (Top15%)Code Elo: 1,566 (Top18%)Elo: 1,570 (Top9%)

Rank #9vs #1

#10Claude Sonnet 5(Anthropic)

Score 82.5

SWE-bench: 73.8% (Top17%)Code Elo: 1,562 (Top20%)Elo: 1,556 (Top16%)

Rank #10vs #1

#11Gemini 3 Pro(Google)

Score 79.4

SWE-bench: 72.4% (Top21%)Code Elo: 1,548 (Top22%)Elo: 1,552 (Top18%)

Rank #11vs #1

#12Gemini 3.7 Flash(Google)

Score 77.9

SWE-bench: 72.4% (Top21%)Code Elo: 1,546 (Top24%)Elo: 1,530 (Top23%)

Rank #12vs #1

Frequently asked questions

Plain-English methodology and leaderboard answers

: Claude Fable 5 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 · best coding llm

Best coding LLM in 2026 (SWE-bench)

Models ranked for repo work using dated SWE-bench snapshots, then price and speed. Not a single lab score.

Weights:SWE-bench 55%Code Elo 25%Elo 20%

Current #1 Ranked PickScore 98.8 / 100

Claude Fable 5

Anthropic · Closed flagship

SWE-bench: 80% (Top 1%)Code Elo: 1,622 (Top 1%)Elo: 1,616 (Top 2%)

SWE-bench: 80%Elo: 1,616

View full model fact sheet

Complete Ranked Category List

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

#1Claude Fable 5(Anthropic)

Score 98.8

SWE-bench: 80% (Top1%)Code Elo: 1,622 (Top1%)Elo: 1,616 (Top2%)

🏆 #1 Overall Leader in Category

#2Claude Opus 5(Anthropic)

Score 98.0

SWE-bench: 79.2% (Top2%)Code Elo: 1,618 (Top3%)Elo: 1,624 (Top1%)

Rank #2vs #1

#3Claude Opus 4.8(Anthropic)

Score 95.0

SWE-bench: 78.4% (Top5%)Code Elo: 1,604 (Top5%)Elo: 1,598 (Top5%)

Rank #3vs #1

#4GPT-5.6 Sol(OpenAI)

Score 94.2

SWE-bench: 77.6% (Top6%)Code Elo: 1,602 (Top7%)Elo: 1,608 (Top4%)

Rank #4vs #1

#5OpenAI o3-mini(OpenAI)

Score 92.7

SWE-bench: 78.5% (Top4%)Code Elo: 1,585 (Top11%)Elo: 1,560 (Top12%)

Rank #5vs #1

#6Claude Opus 4.5(Anthropic)

Score 90.4

SWE-bench: 76.8% (Top8%)Code Elo: 1,574 (Top12%)Elo: 1,568 (Top11%)

Rank #6vs #1

#7GLM-5.3(Zhipu)

Score 90.0

SWE-bench: 76.4% (Top9%)Code Elo: 1,586 (Top9%)Elo: 1,558 (Top14%)

Rank #7vs #1

#8Claude Opus 4.6(Anthropic)

Score 88.9

SWE-bench: 75.9% (Top11%)Code Elo: 1,570 (Top14%)Elo: 1,574 (Top8%)

Rank #8vs #1

#9Gemini 3.6 Pro(Google)

Score 85.5

SWE-bench: 74.6% (Top15%)Code Elo: 1,566 (Top18%)Elo: 1,570 (Top9%)

Rank #9vs #1

#10Claude Sonnet 5(Anthropic)

Score 82.5

SWE-bench: 73.8% (Top17%)Code Elo: 1,562 (Top20%)Elo: 1,556 (Top16%)

Rank #10vs #1

#11Gemini 3 Pro(Google)

Score 79.4

SWE-bench: 72.4% (Top21%)Code Elo: 1,548 (Top22%)Elo: 1,552 (Top18%)

Rank #11vs #1

#12Gemini 3.7 Flash(Google)

Score 77.9

SWE-bench: 72.4% (Top21%)Code Elo: 1,546 (Top24%)Elo: 1,530 (Top23%)

Rank #12vs #1

Frequently asked questions

Plain-English methodology and leaderboard answers

: Claude Fable 5 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