On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...
The overall quant rating is not an average of the factor grades listed. Instead, it gives greater weight to the metrics with the strongest predictive value.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results