Mistral-Small-3.2-24B-Instruct-2506
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
Evaluation results from judge-model scoring across diverse task categories. Scores reflect coherence, accuracy and instruction-following.
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
$0.0900
input / 1M
— stable
$0.2800
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
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=8
Last 30 days
100.0%
n=8
Median response time
6,342ms
n=8
Based on 76 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)
8
OK responses (30d)
8
Total calls (7d)
8
OK responses (7d)
8
Tokonomix benchmark verdicts
Stable performance maintained with expanded category testing
Mistral-Small-3.2-24B-Instruct-2506 continues to demonstrate exceptional performance in this benchmark window, maintaining its perfect quality score of 100.0 across expanded testing. The model now shows consistently high performance across multiple categories including coding, creative writing, instruction following, and multilingual tasks, all scoring at the maximum level. This represents a broader evaluation than the previous window which focused solely on multilingual capabilities. Latency characteristics show notable improvement, with the median response time dropping from 5689ms to 926ms, representing an approximately 84% reduction in typical response times. The 95th percentile latency of 1180ms indicates consistent performance with minimal variation. The model demonstrates particularly strong results in mathematical reasoning and structured data handling, areas that were not evaluated in the baseline window. With 20 test runs completed in this window compared to the single baseline run, the results provide substantially more statistical confidence. Users can expect reliable performance across diverse workloads, from technical programming tasks to creative content generation, with significantly faster response times than initially observed.
Quality
—
Latency p50
—
Test runs
0