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
100.0%
n=9
Last 30 days
100.0%
n=10
Median response time
28,242ms
n=10
Based on 130 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)
10
OK responses (30d)
10
Total calls (7d)
9
OK responses (7d)
9
Tokonomix benchmark verdicts
Claude Sonnet 5.5 debuts with strong coding and vision performance
Claude Sonnet 5.5 enters as Anthropic's latest mid-tier model, demonstrating balanced capabilities across technical and creative tasks. The model achieves 49.0% on SWE-bench Verified, placing it among the stronger coding models currently available, while scoring 64.7% on MMLU-Pro for general knowledge tasks. Instruction following is solid at 79.4% on IFEval, though not category-leading. Vision capabilities show at 59.7% on MMMU, indicating competent multimodal understanding. Mathematical reasoning reaches 73.1% on MATH-500, and agentic behavior scores 47.4% on Tau-bench. The model supports a comprehensive feature set including tool use, vision processing, JSON output modes, PDF input handling, reasoning capabilities, structured schema outputs, and prompt caching for efficiency. With a 200K context window, it handles substantial document processing tasks. As a baseline entry, Claude Sonnet 5.5 establishes itself as a versatile option for developers needing reliable performance across coding, analysis, and multimodal applications without requiring the most powerful tier.
Quality
—
Latency p50
—
Test runs
0