llm-benchmarks
githubdrose.io

Solar Pro 3 Benchmarks


Measured on upstage

41 runs
Avg Tokens / Second
33.75
Avg Time to First Token (ms)
1420.00
Runs Analysed
41
Last Updated
Sep 1, 2026, 04:08 AM

Throughput distribution

Throughput over time

Solar Pro 3upstage1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 39 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
upstageSolar Pro 334.0027.6040.301380.00
upstageSolar Pro 333.5021.1050.201460.00

Frequently Asked Questions

How fast is Solar Pro 3?
The latest rolling average throughput is 33.75 tokens per second with an average time to first token of 1420.00 ms across 41 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 04:08 AM.

Related models