Public
is42day / splink
Benchmark updated: 10/6/202630 Tasks
Fast, accurate and scalable probabilistic data linkage with support for multiple SQL backends
Languages
Python46%JavaScript40.3%Roff12.7%Jinja0.5%Shell0.2%CSS0.1%Other<0.1%
Harness | Input / Output Cost | ||||||
|---|---|---|---|---|---|---|---|
1 |  Mini-SWE-agent | 30 / 30 | $2.95 | $2/$10 | 15m01s |
Key Takeaways
- This 30-task result provides complete benchmark coverage for Claude Sonnet 5 with Mini-SWE-agent.
- The run costs $2.95 per test and has 900.99 seconds of latency.
Cost Analysis
Cost / Test vs. Accuracy
ACCURACYCOST
Average Token Use / Test
Token Usage
InputOutputReasoningCache readCache write
Claude Sonnet 5
Cost is the clearest tradeoff in this comparison. Claude Sonnet 5 leads at 100.00% for $2.95 per test. No other model in this comparison is cheaper.
Latency Analysis
Latency vs. Accuracy
ACCURACYLATENCY
Average Response Time / Test
Response Time
Claude Sonnet 5
Claude Sonnet 5 is both the most accurate and fastest model in this comparison at 100.00% and 15m 1s.