Cost
What it costs to run the model. Not a capability, but it decides model choice as often as any of them, and it is the axis where the ranking inverts: lower is better.
Ordered by how many of these benchmarks put a model in their top 10, then by its best placing. Each column keeps its own ranking; nothing is averaged.
| Model | In top 10 | Artificial Analysis LLM Leaderboard Blended Price, USD per 1M tokens (3:1 input:output) | Artificial Analysis Coding Agents Cost |
|---|---|---|---|
 Apriel v1.5 Thinker servicenow | 1/2 | #1 $0.00 | — |
 DeepSeek V4 Flash deepseek | 1/2 | #42 $0.12 | #1 $0.09 |
| Apriel v1.6 Thinker servicenow | 1/2 | #2 $0.00 | — |
 GPT 6 Luna openai | 1/2 | #57 $0.20 | #2 $0.18 |
 Command A+ cohere | 1/2 | #3 $0.00 | — |
| DeepSeek V4 Pro deepseek | 1/2 | #109 $0.54 | #3 $0.24 |
 G9v3 39A5B ai9star | 1/2 | #4 $0.00 | — |
| GPT 5.6 Luna openai | 1/2 | #92 $0.45 | #4 $0.44 |
| G9v3 ai9star | 1/2 | #5 $0.00 | — |
 Claude Sonnet 5.5 anthropic | 1/2 | #195 $4.00 | #5 $0.48 |
 Gemini 2.0 Flash google | 1/2 | #6 $0.00 | — |
| GPT 6.1 Sol openai | 1/2 | #197 $4.00 | #6 $0.50 |
| Gemma 3 Instruct google | 1/2 | #7 $0.00 | — |
| Gemini 3.8 Flash google | 1/2 | #154 $1.50 | #7 $2.47 |
| Gemma 3n E2B Instruct google | 1/2 | #8 $0.00 | — |
| GPT 6 Sol openai | 1/2 | #196 $4.00 | #8 $2.99 |
| Gemma 4 google | 1/2 | #9 $0.00 | — |
 Muse Spark 1.3 meta | 1/2 | #171 $2.00 | #9 $3.47 |
 K2 Horizon mbzuai | 1/2 | #10 $0.00 | — |
 Qwen 3.8 Max alibaba | 1/2 | #182 $3.00 | #10 $3.48 |
A dash means the board does not list that model — not a score of zero. Entries not yet matched to a model are left out here; they still appear on their own board.