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 Haiku 4.5DeepSeek V3 0324
Claude Haiku 4.5

Anthropic

DeepSeek V3 0324

DeepSeek

Pricing
Input $/1M$1.00$0.27
Output $/1M$5.00$1.12
Blended $/1M (3:1)$2.00$0.483
Cache read $/1M$0.10$0.135
Cache write $/1M$1.25
Quality indices
Intelligence Index29.615.4
Coding Index43.921.2
Math Index41
Agentic Index16.41.5
Speed & latency
Output speed (tok/s)0
Time to first token0s
Time to first answer token0s
Benchmarks (Artificial Analysis)
MMLU-Pro81.9%
GPQA Diamond65.5%
Humanity's Last Exam5.2%
LiveCodeBench40.5%
SciCode35.8%
MATH-50094.2%
AIME52.0%
AIME 202541.0%
IFBench41.0%
AA-LCR (Long Context Reasoning)41.0%
Terminal-Bench Hard15.2%
Terminal-Bench 2.113.9%
τ²-Bench (Telecom)47.1%
τ³-Bench Banking4.5%
Design Arena (Elo)
Website1,149
UI components1,142
Data viz1,160
SVG1,072
3D1,131
Game dev1,155
Code categories1,148
ASCII art1,182
Specs
Context window200K164K
Max output tokens64K66K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek