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 Sonnet 5MiMo-V2.5
Claude Sonnet 5

Anthropic

MiMo-V2.5

Xiaomi

Pricing
Input $/1M$2.00$0.14
Output $/1M$10.00$0.28
Blended $/1M (3:1)$4.00$0.175
Cache read $/1M$0.20$0.0028
Cache write $/1M$2.50
Quality indices
Intelligence Index53.437.2
Coding Index71.556.8
Math Index
Agentic Index46.723.7
Speed & latency
Output speed (tok/s)8863
Time to first token93.55s3.40s
Time to first answer token93.55s34.93s
Benchmarks (Artificial Analysis)
GPQA Diamond91.1%84.9%
Humanity's Last Exam39.6%25.2%
SciCode53.6%43.1%
IFBench67.1%
AA-LCR (Long Context Reasoning)70.7%62.7%
Terminal-Bench Hard41.7%
Terminal-Bench 2.180.5%63.7%
τ²-Bench (Telecom)90.6%
τ³-Bench Banking28.2%6.6%
Design Arena (Elo)
Website1,3141,288
Web apps1,305
Full-stack1,292
Android native1,255
UI components1,3171,294
Data viz1,2811,279
SVG1,2391,218
3D1,3211,273
Game dev1,3451,291
Agentic game dev1,241
Godot game dev1,257
HTML slides1,233
Python→PPTX slides1,252
Code categories1,3121,286
ASCII art1,2301,175
Specs
Context window1M1.05M
Max output tokens128K131K
Input modalitiestext, image, filetext, audio, image, video
TokenizerClaudeOther