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
2,410ms
n=1
Based on 171 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
Major capability expansion adds multimodal tools and advanced features
This benchmark window marks a significant evolution for gpt-5.6-sol with the introduction of eight new capabilities that transform it from a reasoning-focused model into a comprehensive multimodal platform. The model now supports tools, vision, PDF input, JSON mode with schema validation, parallel tool execution, reasoning features, and prompt caching. These additions position it as a full-featured model capable of handling complex workflows that combine visual understanding, structured data processing, and external tool integration. The vision capability enables image analysis and multimodal reasoning tasks. PDF input support allows direct document processing without preprocessing. JSON mode with schema validation ensures reliable structured outputs for API integrations and data pipelines. Parallel tools execution improves efficiency for multi-step operations. Prompt caching should reduce costs and latency for repetitive queries. The core reasoning capabilities that defined the previous baseline remain intact while being augmented by these new modalities. Users gain access to a significantly more versatile model that can handle end-to-end workflows spanning document analysis, visual tasks, structured data generation, and tool-assisted problem solving. This represents one of the most substantial capability expansions in a single benchmark window.
Quality
—
Latency p50
—
Test runs
0