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=23
Median response time
14,958ms
n=23
Based on 397 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)
23
OK responses (30d)
23
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
Major quality leap with 37-point gain, now scoring 94/100 overall
GPT-6-SOL demonstrates a substantial performance improvement in this benchmark window, jumping from 56.8 to 94.0 overall quality score. The 37.2-point increase represents one of the most significant improvements observed between consecutive windows. Coding performance reached a perfect 100, up from 74, while creative tasks scored 90. Reasoning remained consistently strong at 92 across both windows, indicating stable performance in logical tasks. The previous window's notably low factual score of 5 is absent from current metrics, suggesting either category restructuring or significant correction of knowledge retrieval issues. Latency also improved by 19 percent, dropping from 2929ms to 2377ms at the median, though response times remain in the multi-second range. With only 3 test runs in the current window compared to 4 previously, the sample size is limited but results appear promising. The dramatic quality improvement, particularly in coding capabilities, positions this model as a strong performer, though users should monitor whether these gains persist across larger sample sizes in future windows.
Quality
94.0
Latency p50
2,377 ms
Test runs
3
gpt-6-sol
by OpenAI
- Context window
- 1.05M tokens
- Input price
- $2.60 / 1M
- Output price
- $13.00 / 1M
- Tier
- Tier A — Frontier
- Modality
- Text + vision
- API type
- REST · streaming
- Benchmark runs
- 240
More from OpenAI