Benchmark result
dev-model:coding on NVIDIA RTX A2000 12GB +1 more — 77.9 tok/s
Measured with OpenAI-compatible manual on November 11, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
How this run compares
1st fastest of 2 runs of this model on NVIDIA RTX A2000 12GB +1 more · Multi-GPU · median 74.5 tok/s.
sort
- 177.9tok/s88.0OpenAI-compatiblethis run
- 271.0tok/s84.5OpenAI-compatible
Reproduce this run
toolOpenAI-compatible manual
modeldev-model:coding
context131,072
thinkingon
clientv0.4.99+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "dev-model:coding" --tool "OpenAI-compatible"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.