sourc.dev
Home LLMs Tools SaaS APIs
Claude 3.5 Sonnet input $3.00/1M ↓ -50%
GPT-4o input $2.50/1M
Gemini 1.5 Pro input $1.25/1M
Mistral Large input $2.00/1M ↓ -33%
DeepSeek V3 input $0.27/1M
synced 2026-04-05
Claude 3.5 Sonnet input $3.00/1M ↓ -50%
GPT-4o input $2.50/1M
Gemini 1.5 Pro input $1.25/1M
Mistral Large input $2.00/1M ↓ -33%
DeepSeek V3 input $0.27/1M
synced 2026-04-05

Open Weights Leaders

Top-performing open-source and open-weights models ranked by MMLU benchmark score. These models can be self-hosted and fine-tuned.

Methodology: Filtered to open_source=true, then sorted by benchmark_mmlu descending.

# Model Metric
1 Qwen 2.5 72B ◆ OPEN · 86.1% MMLU
2 Mixtral 8x7B ◆ OPEN · 70.6% MMLU
3 Mistral 7B ◆ OPEN · 62.5% MMLU