Loading model…
qwen/qwen3.6-flash4/27 v1 — Nutrition · score 82.8% · pass rate 83.1% (310/373); 4/9 v2 — Resilience · score 69.3% · pass rate 45.8% (210/459)2.4s · output speed 6,248 tok/s$1.08 · prompt tokens 52,795 · completion tokens 721,615$1.08 total, 29/30 cost tests passed).97/125 passed with fast TTFT (2.5s avg) and high output throughput.89/120 passed, outperforming several higher-ranked models in this category.45.8% (210/459), well below the v2 top-3 average of ~53%.1/6 coding_ui passed, 5/9 ui passed — lowest-scoring categories by far.47/120 passed (39.2%), indicating difficulty with structural code changes.grok-4.3 by 2.6 pp score and `Overall score % from merged run_models rows (chronological). Only runs that include this model appear as points.
Overall score % from the most recent run per selected suite version for this model. Different suites use different fixtures and max scores — only interpret comparisons qualitatively.
No score samples for the selected versions.
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).