Loading model…
deepseek/deepseek-v4-pro13 (v1=23, v2=3). v1 — Nutrition: 23/27, score 15.2%, pass rate 15% (56/373). v2 — Resilience: 3/14, score 73.8%, pass rate 52.7% (242/459).2.2s, output speed 413 tok/s$0.90, prompt tokens 46005, completion tokens 2803723/14) with solid pass rate (52.7%) across 459 tests.30/30 on cost tests, lowest cost sum ($0.016) in that category.55/60, 91.7%) and solid speed category results (56/125 passed).23/27) with very low pass rate (15%) — significant gap vs top models.0/6), indicating UI generation struggles.24/122, 19.7%) and refactoring (18/120, 15%).x-ai/grok-4.3 (85.5%, `86.1%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).