What is the best open source llm right now?

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

How is this list ranked?

Highest reasoning signal among models you can self-host or buy as open weights. Weights: Elo 30%, LiveBench 30%, GPQA 25%, Out $ 15%.

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 open source llm

Best open-source LLM in 2026

Open-weight models ranked on preference Elo, LiveBench, and SWE-bench. Check the license before you ship.

Weights:Elo 30%LiveBench 30%GPQA 25%Out $ 15%

Current #1 Ranked PickScore 77.5 / 100

DeepSeek V4 Pro

DeepSeek · Open weights

Elo: 1,536 (Top 22%)LiveBench: 70.1% (Top 18%)GPQA: 84% (Top 18%)Out $: $1.6/1M (Top 40%)

SWE-bench: 71.6%Elo: 1,536

View full model fact sheet

Complete Ranked Category List

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

#1DeepSeek V4 Pro(DeepSeek)

Score 77.5

Elo: 1,536 (Top22%)LiveBench: 70.1% (Top18%)GPQA: 84% (Top18%)Out $: $1.6/1M (Top40%)

🏆 #1 Overall Leader in Category

#2DeepSeek V4 Flash(DeepSeek)

Score 71.6

Elo: 1,490 (Top39%)LiveBench: 67.8% (Top29%)GPQA: 81.6% (Top29%)Out $: $0.28/1M (Top5%)

Rank #2vs #1

#3Qwen QwQ 32B(Alibaba)

Score 70.7

Elo: 1,495 (Top34%)LiveBench: 68% (Top27%)GPQA: 83.2% (Top23%)Out $: $1.2/1M (Top35%)

Rank #3vs #1

#4GLM-5.2(Zhipu)

Score 61.2

Elo: 1,492 (Top36%)LiveBench: 65.2% (Top40%)GPQA: 79.5% (Top39%)Out $: $1.8/1M (Top42%)

Rank #4vs #1

#5GLM-5V Turbo(Zhipu)

Score 56.0

Elo: 1,475 (Top45%)LiveBench: 63.8% (Top51%)GPQA: 77.4% (Top49%)Out $: $0.6/1M (Top20%)

Rank #5vs #1

#6MiniMax M2.5(MiniMax)

Score 53.5

Elo: 1,478 (Top43%)LiveBench: 64.4% (Top46%)GPQA: 76.2% (Top58%)Out $: $1.2/1M (Top35%)

Rank #6vs #1

#7Qwen3 235B(Alibaba)

Score 48.9

Elo: 1,440 (Top61%)LiveBench: 63.5% (Top54%)GPQA: 76.8% (Top51%)Out $: $0.88/1M (Top26%)

Rank #7vs #1

#8Llama 4 Maverick(Meta)

Score 48.6

Elo: 1,468 (Top50%)LiveBench: 62.8% (Top58%)GPQA: 74.6% (Top64%)Out $: $0.6/1M (Top20%)

Rank #8vs #1

#9Qwen 2.5 Coder 32B(Alibaba)

Score 46.3

Elo: 1,425 (Top65%)LiveBench: 64.8% (Top44%)GPQA: 74% (Top70%)Out $: $0.72/1M (Top23%)

Rank #9vs #1

#10DeepSeek R1(DeepSeek)

Score 37.8

Elo: 1,358 (Top80%)LiveBench: 59% (Top74%)GPQA: 79.8% (Top36%)Out $: $2.19/1M (Top47%)

Rank #10vs #1

#11Qwen3.8 27B(Alibaba)

Score 37.5

Elo: 1,398 (Top73%)LiveBench: 60.6% (Top68%)GPQA: 73.4% (Top73%)Out $: $0.4/1M (Top13%)

Rank #11vs #1

#12Llama 4 Scout(Meta)

Score 36.5

Elo: 1,412 (Top68%)LiveBench: 59.6% (Top73%)GPQA: 71.2% (Top80%)Out $: $0.3/1M (Top8%)

Rank #12vs #1

Frequently asked questions

Plain-English methodology and leaderboard answers

: DeepSeek V4 Pro 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 open source llm

Best open-source LLM in 2026

Open-weight models ranked on preference Elo, LiveBench, and SWE-bench. Check the license before you ship.

Weights:Elo 30%LiveBench 30%GPQA 25%Out $ 15%

Current #1 Ranked PickScore 77.5 / 100

DeepSeek V4 Pro

DeepSeek · Open weights

Elo: 1,536 (Top 22%)LiveBench: 70.1% (Top 18%)GPQA: 84% (Top 18%)Out $: $1.6/1M (Top 40%)

SWE-bench: 71.6%Elo: 1,536

View full model fact sheet

Complete Ranked Category List

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

#1DeepSeek V4 Pro(DeepSeek)

Score 77.5

Elo: 1,536 (Top22%)LiveBench: 70.1% (Top18%)GPQA: 84% (Top18%)Out $: $1.6/1M (Top40%)

🏆 #1 Overall Leader in Category

#2DeepSeek V4 Flash(DeepSeek)

Score 71.6

Elo: 1,490 (Top39%)LiveBench: 67.8% (Top29%)GPQA: 81.6% (Top29%)Out $: $0.28/1M (Top5%)

Rank #2vs #1

#3Qwen QwQ 32B(Alibaba)

Score 70.7

Elo: 1,495 (Top34%)LiveBench: 68% (Top27%)GPQA: 83.2% (Top23%)Out $: $1.2/1M (Top35%)

Rank #3vs #1

#4GLM-5.2(Zhipu)

Score 61.2

Elo: 1,492 (Top36%)LiveBench: 65.2% (Top40%)GPQA: 79.5% (Top39%)Out $: $1.8/1M (Top42%)

Rank #4vs #1

#5GLM-5V Turbo(Zhipu)

Score 56.0

Elo: 1,475 (Top45%)LiveBench: 63.8% (Top51%)GPQA: 77.4% (Top49%)Out $: $0.6/1M (Top20%)

Rank #5vs #1

#6MiniMax M2.5(MiniMax)

Score 53.5

Elo: 1,478 (Top43%)LiveBench: 64.4% (Top46%)GPQA: 76.2% (Top58%)Out $: $1.2/1M (Top35%)

Rank #6vs #1

#7Qwen3 235B(Alibaba)

Score 48.9

Elo: 1,440 (Top61%)LiveBench: 63.5% (Top54%)GPQA: 76.8% (Top51%)Out $: $0.88/1M (Top26%)

Rank #7vs #1

#8Llama 4 Maverick(Meta)

Score 48.6

Elo: 1,468 (Top50%)LiveBench: 62.8% (Top58%)GPQA: 74.6% (Top64%)Out $: $0.6/1M (Top20%)

Rank #8vs #1

#9Qwen 2.5 Coder 32B(Alibaba)

Score 46.3

Elo: 1,425 (Top65%)LiveBench: 64.8% (Top44%)GPQA: 74% (Top70%)Out $: $0.72/1M (Top23%)

Rank #9vs #1

#10DeepSeek R1(DeepSeek)

Score 37.8

Elo: 1,358 (Top80%)LiveBench: 59% (Top74%)GPQA: 79.8% (Top36%)Out $: $2.19/1M (Top47%)

Rank #10vs #1

#11Qwen3.8 27B(Alibaba)

Score 37.5

Elo: 1,398 (Top73%)LiveBench: 60.6% (Top68%)GPQA: 73.4% (Top73%)Out $: $0.4/1M (Top13%)

Rank #11vs #1

#12Llama 4 Scout(Meta)

Score 36.5

Elo: 1,412 (Top68%)LiveBench: 59.6% (Top73%)GPQA: 71.2% (Top80%)Out $: $0.3/1M (Top8%)

Rank #12vs #1

Frequently asked questions

Plain-English methodology and leaderboard answers

: DeepSeek V4 Pro 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