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.
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
2,914ms
n=1
Based on 121 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
Grok 4.6 debuts with strong performance across core benchmarks
Grok 4.6 enters the benchmark landscape as xAI's first evaluated model in this tracking window, establishing baseline performance metrics across multiple domains. The model demonstrates particularly strong performance in mathematical reasoning, achieving 89.4% on MATH-500 and 93.8% on GSM8K, placing it competitively among frontier models. Coding capabilities are robust with 86.5% on HumanEval and 79.6% on LiveCodeBench, indicating solid software engineering capabilities. Academic knowledge shows strength at 88.6% on MMLU-Pro, though GPQA performance at 56.4% suggests room for improvement in graduate-level science questions. Multimodal capabilities are present with 74.3% on MMMU, establishing vision-language integration. The model supports JSON output, tool use, and reasoning modes, providing developers with flexible interaction patterns. With a 128K token context window, Grok 4.6 handles substantial documents and conversations. As a baseline entry, these metrics establish xAI's position in the competitive landscape, showing particular strength in mathematical and coding tasks while maintaining competent performance across general knowledge domains. Future benchmark windows will reveal how the model evolves relative to this initial showing.
Quality
—
Latency p50
—
Test runs
0