Public
aimacode / aima-java
Benchmark updated: 9/24/202630 Tasks
Java implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
Languages
Java86.4%Jupyter Notebook13.6%Python<0.1%
Harness | Input / Output Cost | ||||||
|---|---|---|---|---|---|---|---|
1 |  Mini-SWE-agent | 28 / 30 | $0.29 | $1/$5 | 3m22s |
Key Takeaways
- This 30-task result is a strong single-run benchmark outcome, with 2 tasks unresolved.
- The run completes in 201.60 seconds on average.
Cost Analysis
Cost / Test vs. Accuracy
ACCURACYCOST
Average Token Use / Test
Token Usage
InputOutputReasoningCache readCache write
Claude Haiku 4.5 (Thinking)
Cost is the clearest tradeoff in this comparison. Claude Haiku 4.5 (Thinking) leads at 93.33% for $0.29 per test. No other model in this comparison is cheaper.
Latency Analysis
Latency vs. Accuracy
ACCURACYLATENCY
Average Response Time / Test
Response Time
Claude Haiku 4.5 (Thinking)
Claude Haiku 4.5 (Thinking) is both the most accurate and fastest model in this comparison at 93.33% and 3m 22s.