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
94.1%
n=17
Last 30 days
94.4%
n=18
Median response time
17,715ms
n=17
Based on 142 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)
18
OK responses (30d)
17
Total calls (7d)
17
OK responses (7d)
16
Tokonomix benchmark verdicts
gpt-6.1-sol debuts with strong coding performance and vision capabilities
OpenAI's gpt-6.1-sol enters benchmarking as a capable model with notable strengths in programming tasks and multimodal processing. The model demonstrates exceptional performance in HumanEval at 95.1% and strong results in MBPP at 86.3%, positioning it as a solid choice for code generation and technical tasks. Mathematical reasoning shows competence with 88.7% on GSM8K, though MATH performance at 74.2% suggests room for improvement on more advanced problems. General knowledge and reasoning capabilities are well-balanced, with MMLU at 86.4% and ARC Challenge at 96.4% indicating strong foundational understanding. The model supports a comprehensive feature set including vision processing, JSON output modes, PDF input handling, and reasoning capabilities. Multimodal performance on MMMU reaches 69.8%, demonstrating adequate vision-language integration. Context handling extends to 200K tokens with reported caching support, suitable for long-document applications. As a baseline entry, gpt-6.1-sol establishes itself as a versatile model with particular strength in coding domains, though future benchmarks will reveal performance trajectory and consistency across updates.
Quality
—
Latency p50
—
Test runs
0