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
LLM Rankings

Leaderboards

10 rankings computed from verified data. Updated when underlying data changes. No editorial weighting.

Biggest Price Collapse
Largest % reduction from GPT-3 baseline ($60/1M tokens)
1 Gemini 1.5 Flash ↓99.9% from $60
2 Gemini 2.0 Flash ↓99.8% from $60
3 Llama 3.3 70B ↓99.8% from $60
View full leaderboard →
Largest Context Window
Models ranked by maximum context window size in tokens
1 Gemini 1.5 Pro 2,000,000 tokens
2 Gemini 1.5 Flash 1,000,000 tokens
3 Gemini 2.0 Flash 1,000,000 tokens
View full leaderboard →
Lowest Input Price
Active models ranked by input cost per million tokens
1 Gemini 1.5 Flash $0.07 / 1M tokens
2 Gemini 2.0 Flash $0.10 / 1M tokens
3 Llama 3.3 70B $0.10 / 1M tokens
View full leaderboard →
Highest Benchmark
Models ranked by MMLU score — reasoning across 57 subjects
1 o1 92.3% MMLU
2 DeepSeek R1 90.8% MMLU
3 Qwen3 235B A22B 88.9% MMLU
View full leaderboard →
Longest Tracked
Models we have been tracking the longest on sourc.dev
1 Claude 3 Sonnet Since 2026-03-24 — 11 days
2 Claude 3 Opus Since 2026-03-24 — 11 days
3 Claude 3 Haiku Since 2026-03-24 — 11 days
View full leaderboard →
EU Data Residency Leaders
Top-performing models available with EU data residency
1 Llama 3.1 405B EU ✓ · 88.6% MMLU
2 Qwen 2.5 72B EU ✓ · 86.1% MMLU
3 Llama 3.3 70B EU ✓ · 86.0% MMLU
View full leaderboard →
Open Weights Leaders
Top-performing open-source / open-weights models by MMLU
1 Qwen 2.5 72B ◆ OPEN · 86.1% MMLU
2 Mixtral 8x7B ◆ OPEN · 70.6% MMLU
3 Mistral 7B ◆ OPEN · 62.5% MMLU
View full leaderboard →
Best Value
Highest benchmark score per dollar of input cost
1 Gemini 1.5 Flash 1052.0 score/$1
2 Gemini 2.0 Flash 879.0 score/$1
3 Llama 3.3 70B 860.0 score/$1
View full leaderboard →
Most Context Per Dollar
Largest context window relative to input token cost
1 Gemini 1.5 Flash 13,333,333 tokens/$1
2 Gemini 2.0 Flash 10,000,000 tokens/$1
3 Gemini 1.5 Pro 1,600,000 tokens/$1
View full leaderboard →
Submit a model or correction →