AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Opus 4.6DeepSeek V3.1 Terminus
Claude Opus 4.6

Anthropic

DeepSeek V3.1 Terminus

DeepSeek

Pricing
Input $/1M$5.00$0.27
Output $/1M$25.00$1.00
Blended $/1M (3:1)$10.00$0.453
Cache read $/1M$0.50$0.135
Cache write $/1M$6.25
Quality indices
Intelligence Index26.413.9
Coding Index43.5
Math Index53.7
Agentic Index6.8
Speed & latency
Output speed (tok/s)00
Time to first token0s0s
Time to first answer token0s0s
Benchmarks (Artificial Analysis)
MMLU-Pro83.6%
GPQA Diamond84.0%75.1%
Humanity's Last Exam19.1%8.7%
LiveCodeBench52.9%
AIME 202553.7%
IFBench44.6%41.2%
AA-LCR (Long Context Reasoning)67.0%45.3%
Terminal-Bench Hard48.5%31.8%
τ²-Bench (Telecom)84.8%37.1%
Design Arena (Elo)
Website1,3031,199
Web apps1,219
Full-stack1,229
Mobile apps1,238
Android native1,216
UI components1,3001,198
Data viz1,2961,183
SVG1,2511,088
3D1,3031,169
Game dev1,3011,154
Agentic game dev1,215
Code categories1,3041,190
ASCII art1,273
Specs
Context window1M164K
Max output tokens128K33K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek