Public
conjfrnk / memovox
Benchmark updated: 8/13/202630 Tasks
A local-first multimodal video-to-knowledge engine.
Languages
Python97.9%JavaScript2%Makefile0.1%Dockerfile<0.1%
Harness | Input / Output Cost | ||||||
|---|---|---|---|---|---|---|---|
1 |  Mini-SWE-agent | 27 / 30 | $2.81 | $5/$25 | 11m05s | ||
2 | Mini-SWE-agent | 25 / 30 | $0.06 | $0.2/$1.2 | 4m17s |
Key Takeaways
- Claude Opus 5 with Mini-SWE-agent scores 90%, compared with 83.33% for GPT-5.6 Luna with Mini-SWE-agent.
- GPT-5.6 Luna with Mini-SWE-agent costs $0.06 per test and takes 257.46 seconds, versus $2.81 and 665.35 seconds for Claude Opus 5.
Cost Analysis
Cost / Test vs. Accuracy
ACCURACYCOST
Average Token Use / Test
Token Usage
InputOutputReasoningCache readCache write
Claude Opus 5
GPT-5.6 Luna
Cost is the clearest tradeoff in this comparison. Claude Opus 5 leads at 90.00% for $2.81 per test. GPT-5.6 Luna is the lower-cost option at 83.33% for $0.06 per test.
Latency Analysis
Latency vs. Accuracy
ACCURACYLATENCY
Average Response Time / Test
Response Time
Claude Opus 5
GPT-5.6 Luna
Latency separates several models with similarly strong scores. Claude Opus 5 leads at 90.00%, while GPT-5.6 Luna is fastest at 4m 17s with 83.33% accuracy.