Loading model…
openai/gpt-5.3-codex1/14 in v2 — Resilience, score 77.7%, pass rate 61.2% (281/459)1.01s, output speed 107.2 tok/s$2.63, prompt tokens 29117, completion tokens 1861481/14) in Resilience with strong coding performance (58/60 passed, 99.6% score).30/30 on cost tests, lowest cost per token among top models.107 tok/s) with low TTFT (1.01s), suitable for interactive use.21/60 passed (74.6% score), the lowest category pass rate.13/60 passed (67.1% score), second-weakest category.31/60 passed (73.0% score), below overall average.moonshotai/kimi-k2.6 (74.8%, 60.6%) and deepseek/deepseek-v4-pro (73.8%, 52.7%) by 2.8–3.9 points in score and up to 8.5 points in pass rate.GPT-
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).