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
968ms
n=1
Based on 125 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-5.6-terra debuts with strong performance across all benchmarks
OpenAI's gpt-5.6-terra establishes a strong baseline with exceptional performance across coding, reasoning, and multimodal tasks. The model demonstrates particular strength in mathematical reasoning, scoring 94.8 on MATH500 and 96.5 on GSM8K, positioning it among the top-tier models for quantitative problem-solving. Coding capabilities are robust with 86.2 on HumanEval and 83.4 on MultiPL-E, while the 74.5 SWE-bench Verified score indicates solid real-world software engineering aptitude. Vision capabilities show competency across MMMU (73.2) and various visual question answering benchmarks, though with room for improvement compared to the model's text-based strengths. The instruction-following score of 87.8 on IFEval suggests reliable adherence to user constraints. Reasoning performance is notable, with 78.4 on GPQA Diamond and 84.6 on MMLU-Pro. The model ships with a comprehensive feature set including tools, vision, JSON modes, PDF input, reasoning capabilities, schema validation, parallel tool execution, and prompt caching. As an initial release, gpt-5.6-terra establishes itself as a versatile foundation model suitable for diverse enterprise and development workflows.
Quality
—
Latency p50
—
Test runs
0