moonshotai/kimi-k2.7-code23/30 in v2 — Resilience, score 65.7%, pass rate 51.4% (236/459)0.91s, output speed 93.4 tok/s$1.75, prompt tokens 30,053, completion tokens 441,99751/60 passed, 85% pass rate)26/30 passed, 86.7% pass rate)38/60 passed, 63.3% pass rate)5/60 passed, only 8.3% pass rate)14/60 passed, 23.3% pass rate)23/60 passed, 38.3% pass rate)openai/gpt-5.5 (score 77.9%, pass rate 61.9%), openai/gpt-5.3-codex (77.7%, 61.2%), and qwen/qwen3.7-max (75.3%, 54.9%).Ranked 23/30 in Resilience, this model suits cost-sensitive coding tasks but carries deployment risk for complex refactoring and reasoning workloads.
Overall score % from merged run_models rows (chronological). Only runs that include this model appear as points.
Score % vs pass rate % per category. With 0/1 scorers, both usually line up; with proportional tests, score % reflects partial credit while pass rate counts tests that clear the fixture threshold.
Total estimated spend per scope for this model (bars, left axis) and mean spend per merged result row (line, right axis: total ÷ tests).
Pass rate % per difficulty level — complements the score % view above.
Normalized 0–100 within this model: TTFT (shorter → higher spoke) and decode tok/s (higher → higher spoke). Values come from streamed BLXBench runs merged into overall_ranking.json.
Pass rate % per category for this model (distinct from score %, which reflects partial credit).