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
$0.1300
input / 1M
— stable
$0.1300
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
Quality rebounds to 81.5 with strong gains in factual and reasoning performance
Mistral-Nemo-Instruct-2407 demonstrates significant recovery in this benchmark window, with overall quality climbing from 61.3 to 81.5, marking a 20.2 point improvement. The model has addressed its previous factual performance weakness, surging from 25 to 94 in that category. Reasoning capabilities emerged as a new strength at 96, while coding performance remains robust at 92, down slightly from the previous perfect 100. The most notable concern is creative performance, which registers at just 44, representing a gap in the model's capabilities that users should consider for content generation tasks. Latency has improved substantially with a 27% reduction, bringing p50 response time down to 3505ms from 4815ms. The multilingual category, which scored 59 previously, was not evaluated in the current window. With five test runs compared to four previously, this assessment provides a solid view of the model's improved stability across technical and analytical workloads. Users requiring strong factual accuracy and reasoning will find this version considerably more reliable, though those prioritizing creative output may need to evaluate alternatives.
Quality
81.5
Latency p50
3,505 ms
Test runs
5