Loading model…
qwen/qwen3.7-max3/24 in v2 — Resilience, score 75.27%, pass rate 54.9% (252/459)1.27s, output speed 223.27 tok/s$1.88, prompt tokens 31,989, completion tokens 242,79154/60 passed, score 250/2619/9 passed29/30 passed, score 134/15011/60 passed, score 378/5416/60 passed, score 361/54121/60 passed, score 330/512openai/gpt-5.5 (77.9%, 61.9% pass rate) and openai/gpt-5.3-codex (77.7%, 61.2% pass rate) with 75.27% score and 54.9% pass rate.Ranked 3/24 in Resilience, this model offers solid coding and cost efficiency but shows significant gaps in reasoning, refactoring, and security. Suitable for deployment where these weaker categories are not critical, with moderate risk for complex reasoning tasks.
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).