Open-weight rankingData updated · May 6, 202612 ranked models

Best Open-weight AI Models

A ranked view of models with available weights. The page says open-weight because licensing terms vary, and missing license metadata is shown plainly instead of assumed.

Rank 1Medium confidence

DeepSeek

Composite score
Rank 2Medium confidence

DeepSeek

Composite score
Rank 3High confidence

DeepSeek

Composite score

Scores are based on the visible benchmark set and available metadata.

Missing prices stay missing
RankModelScoreEvidenceInput priceContext
#1R1 0528
DeepSeek
83.63 benchmarks · Medium$0.50/M164K
#2R1
DeepSeek
73.93 benchmarks · Medium$0.70/M64K
#3DeepSeek V3
DeepSeek
71.15 benchmarks · High$0.32/M164K
#4Qwen2.5 72B Instruct
Alibaba Qwen
69.76 benchmarks · High$0.36/M33K
#5Phi 4
Microsoft
69.44 benchmarks · High$0.07/M16K
#6Qwen3 235B A22B
Alibaba Qwen
66.53 benchmarks · Medium$0.46/M131K
#7Qwen2.5 Coder 32B Instruct
Alibaba Qwen
61.44 benchmarks · High$0.66/M33K
#8Llama 3.1 405B
Meta
59.45 benchmarks · HighNot listed/MNot listed
#9Qwen2.5 Coder 7B Instruct
Alibaba Qwen
54.73 benchmarks · Medium$0.03/M33K
#10Llama 3.1 70B Instruct
Meta
54.24 benchmarks · High$0.40/M131K
#11Llama 3.3 70B Instruct (free)
Meta
51.73 benchmarks · MediumNot listed/M66K
#12Mistral Large 2407
Mistral AI
47.83 benchmarks · Medium$2.00/M131K
Strict caveat

Open-weight does not automatically mean free, unrestricted, or commercially usable. Check the listed license and provider terms before deployment.

BenchGecko ranks models from published benchmark scores and model metadata. Scores do not measure every use case, and missing data can affect rankings.

Related ranking

Coding models ranked from published coding benchmark scores, listed prices, and model metadata tracked by BenchGecko.

Related ranking

Reasoning models ranked from public benchmark scores across GPQA Diamond, BBH, ARC-AGI, SimpleBench, and related tests.

Related ranking

Math models ranked from public benchmark scores across GSM8K, MATH-level tests, AIME-style tasks, and FrontierMath where available.

Why does this page say open-weight instead of open-source?

Model weights can be available while license terms still vary. Open-weight is a more precise public label unless the license is fully verified.

Are open-weight models free to run?

The model file may be available, but inference still has compute cost. BenchGecko shows pricing metadata when it is listed.

How are open-weight models ranked?

Models need multiple published benchmark scores. Scores are normalized across benchmarks, then adjusted slightly for evidence coverage.