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
2,505ms
n=1
Based on 154 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 4.20 Reasoning maintains strong performance across benchmarks
Grok 4.20 Reasoning (0309) shows stable performance across the benchmark window with minimal variation from its previous evaluation. The model continues to demonstrate strong coding capabilities with MBPP at 82.7% and HumanEval at 91.5%, placing it competitively among leading models. Mathematical reasoning remains robust with 85.0% on GSM8K and 74.6% on MATH, though trailing some specialized models in this domain. Visual understanding through MMMU-Pro achieves 57.0%, indicating solid multi-modal performance. The model's reasoning capabilities are reflected in strong GPQA performance at 60.1%. Instruction following on IFEval maintains a respectable 66.5% strict score. Overall benchmark scores place Grok 4.20 Reasoning at 69.8% simple average and 68.2% weighted, representing consistent high-tier performance without significant regression or breakthrough improvements. The model continues to excel in coding tasks while maintaining balanced capabilities across mathematical, visual, and reasoning domains. Users can expect reliable performance for complex reasoning tasks, code generation, and multi-modal applications, though mathematical problem-solving may require additional verification for specialized use cases.
Quality
—
Latency p50
—
Test runs
0