Archived
This model has been discontinued by the provider. Historical data is preserved.
No longer available since June 30, 2027.
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 history
Direct provider rates per million tokens, plus a typical-conversation cost estimate.
Pricing over time
Input & output per 1M tokens · step-line = price changes
$3.00
input / 1M
— stable
$15.00
output / 1M
— stable
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
No measurements yet
We haven't recorded enough API calls to show availability stats for this model. Data appears once the model starts receiving live traffic.
Tokonomix benchmark verdicts
Claude Sonnet 5 shows no benchmark data despite seven new capabilities
Claude Sonnet 5 continues to report no benchmark performance data across any standard evaluation metrics for the second consecutive window. The model has maintained its seven recently added capabilities: tools, vision, json_mode, pdf_input, reasoning, json_schema, and prompt_caching. However, without quantitative performance measurements, users cannot assess how this model compares to alternatives or previous versions on key dimensions like accuracy, reasoning quality, or task completion rates. The absence of benchmark data makes it impossible to verify whether the added capabilities translate into measurable improvements in real-world performance. For organizations evaluating Claude Sonnet 5, the lack of transparent metrics presents a challenge in making informed deployment decisions. The model's actual capabilities in areas like visual understanding, structured output generation, or tool use remain unquantified through independent testing. Users considering this model should seek empirical validation through their own testing protocols before committing to production use, as public benchmark performance remains unavailable to guide selection decisions.
Quality
—
Latency p50
—
Test runs
0