Loading model…
openai/gpt-5.5-pro20/27 + score 22% + pass rate 22% (163/732)12.5s + output speed 2215 tok/s$7.88, prompt tokens 16190, completion tokens 4154846/120 passed (38%), the strongest area.41/120 (34%).32/130 passes, indicating reasonable responsiveness.2/120 passed (2%).22% ranks near bottom third of leaderboard.x-ai/grok-4.3 by 63 percentage points in score (85% vs 22%).86% (Grok) vs 22% (GPT-5.5 Pro).openai/gpt-chat-latest scores 84%, far ahead.This model is unsuitable for production coding tasks requiring reliability. Its severe hallucination failures and low reasoning scores pose high deployment risk. Consider only for non-critical speed-focused tasks where security is not paramount.
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).