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 4.5Gemma 4 31B
Claude Haiku 4.5

Anthropic

Gemma 4 31B

Google

Pricing
Input $/1M$1.00$0.12
Output $/1M$5.00$0.37
Blended $/1M (3:1)$2.00$0.182
Cache read $/1M$0.10
Cache write $/1M$1.25
Quality indices
Intelligence Index29.629.4
Coding Index43.943.4
Math Index
Agentic Index16.414.4
Speed & latency
Output speed (tok/s)35
Time to first token0.98s
Time to first answer token50.29s
Benchmarks (Artificial Analysis)
GPQA Diamond85.7%
Humanity's Last Exam22.7%
SciCode43.4%
IFBench75.6%
AA-LCR (Long Context Reasoning)62.0%
Terminal-Bench Hard36.4%
Terminal-Bench 2.143.4%
τ²-Bench (Telecom)59.9%
τ³-Bench Banking15.1%
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 tokens64K16K
Input modalitiestext, image, fileimage, text, video
TokenizerClaudeGemma