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 4.5Mistral Small 4
Claude Haiku 4.5

Anthropic

Mistral Small 4

Mistral

Pricing
Input $/1M$1.00$0.15
Output $/1M$5.00$0.60
Blended $/1M (3:1)$2.00$0.262
Cache read $/1M$0.10$0.015
Cache write $/1M$1.25
Quality indices
Intelligence Index29.619.6
Coding Index43.926.6
Math Index
Agentic Index16.44.7
Speed & latency
Output speed (tok/s)175
Time to first token0.53s
Time to first answer token11.93s
Benchmarks (Artificial Analysis)
GPQA Diamond76.9%
Humanity's Last Exam9.5%
SciCode38.0%
IFBench48.2%
AA-LCR (Long Context Reasoning)44.7%
Terminal-Bench Hard17.4%
Terminal-Bench 2.121.0%
τ²-Bench (Telecom)41.2%
τ³-Bench Banking5.2%
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 window200K262K
Max output tokens64K
Input modalitiestext, image, filetext, image
TokenizerClaudeMistral