Speed analysis
Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.
Quality scores
How this model compares to the rest of the field on each prompt category, from a pairwise fit over the same prompts. The raw judge score sits underneath each number.
Win rate per category: how often this model beats a field-average model on a prompt from that category. 50% is average, not a failing grade. It is not a percentage of correct answers.
Pricing
What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.
Tokens per second
Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.
Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.
Capabilities
Availability
Availability
How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.
Last 7 days
—
Last 30 days
100.0%
n=1
Median response time
1,205ms
n=1
Based on 375 measurements over the last 30 days.
Technical details
Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.
Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.
Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.
Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.
Total calls (30d)
1
OK responses (30d)
1
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
gpt-6-luna achieves significant quality gains with 43% faster response times
OpenAI's gpt-6-luna demonstrates substantial improvement across multiple dimensions in this benchmark window. The overall quality score jumped from 82.8 to 94.7, representing an 11.9 point increase that places it among top-tier models. Most notably, coding performance surged from 74 to a perfect 100, suggesting major enhancements to the model's programming capabilities. Response latency improved dramatically, with p50 times dropping from 5196ms to 2959ms, a 43% reduction that should meaningfully improve user experience. Reasoning scores held steady at 92, indicating consistent logical performance. A new creative writing category emerged with a score of 92, though direct comparison is unavailable. The benchmark window remains limited with only 3 test runs, which constrains statistical confidence but shows clear directional improvement. Users working with coding tasks will likely see the most dramatic benefits, while those focused on reasoning can expect maintained quality with significantly faster delivery. The combination of quality and speed improvements suggests meaningful architectural or optimization work between versions.
Quality
94.7
Latency p50
2,959 ms
Test runs
3
gpt-6-luna
by OpenAI
- Context window
- 1.05M tokens
- Input price
- $0.2000 / 1M
- Output price
- $0.9800 / 1M
- Tier
- Tier B — Production
- Modality
- Text + vision
- API type
- REST · streaming
- Benchmark runs
- 241
More from OpenAI