GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
There was an error while loading.
Key facts
- This is related to #29353, which reported a task-level reproduction where gpt-5.5 runs ending at exactly 516 reasoning tokens returned the wrong answer
- The clustering is also not evenly distributed across models. gpt-5.5 accounts for only 19.3% of responses but 82.0% of exact-516 events
- The fixed values are also notable: 516, 1034, and 1552 look like repeated threshold boundaries rather than a naturally varying reasoning-token distribution
- Gpt-5.5 responses cluster heavily at exactly 516 reasoning tokens, with related spikes around 1034 and 1552
Summary
The reporter found an aggregate pattern in Codex token_count metadata: gpt-5.5 responses disproportionately land at exactly reasoning_output_tokens = 516, with additional fixed-boundary spikes around 1034 and 1552. This appears model-specific and coincides with lower overall reasoning-token intensity, which may help explain degraded performance on complex/high-stakes Codex tasks. This is related to #29353, which reported a task-level reproduction where gpt-5.5 runs ending at exactly 516 reasoning tokens returned the wrong answer. Time window analyzed: Feb 1-Jun 27, 2026 UTC. Related issue: gpt-5.5 xhigh sometimes short-circuits with reasoning_output_tokens=516 and wrong final_answer in Codex Desktop #29353.