Updated March 26, 2026· Based on independent benchmark data
GPT-5.2 Codex (xhigh) and GPT-5.1 (high) are virtually tied on intelligence (49.0 vs 47.7).
| Metric | GPT-5.2 Codex (xhigh) | GPT-5.1 (high) |
|---|---|---|
| Intelligence Score | 49.0 | 47.7 |
| Coding Score | 43.0 | 44.7 |
| Math Score | N/A | 94.0 |
| Speed (tok/s) | 99 tok/s | 92 tok/s |
| Latency (TTFT) | 6.86s | 39.04s |
| Input Price / 1M tokens | $1.75 | $1.25 |
| Output Price / 1M tokens | $14 | $10 |
| Context Window | N/A | N/A |
GPT-5.2 Codex (xhigh) and GPT-5.1 (high) perform similarly on overall intelligence, scoring 49.0 and 47.7 respectively. Their coding capabilities are closely matched (43.0 vs 44.7).
Both models deliver similar output speeds: GPT-5.2 Codex (xhigh) at 99 tok/s and GPT-5.1 (high) at 92 tok/s. Time to first token is 6.86s for GPT-5.2 Codex (xhigh) vs 39.04s for GPT-5.1 (high), which affects perceived responsiveness in interactive applications.
GPT-5.1 (high) is more affordable at $1.25/1M input tokens ($10/1M output), while GPT-5.2 Codex (xhigh) costs $1.75/1M input ($14/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, GPT-5.2 Codex (xhigh) would cost approximately $10.50/month vs $7.50/month for GPT-5.1 (high) in input costs alone.
GPT-5.1 (high) scores higher on coding benchmarks (44.7 vs 43.0), making it the better choice for programming tasks.
GPT-5.1 (high) is cheaper at $1.25/1M input tokens vs $1.75/1M for GPT-5.2 Codex (xhigh).
GPT-5.2 Codex (xhigh) is faster, producing output at 99 tok/s compared to GPT-5.1 (high)'s 92 tok/s.
No, GPT-5.2 Codex (xhigh) does not support image input. Neither model supports image input.
Data last synced: March 26, 2026
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
| Output Modalities | Text | Text |
| Free Tier | No | No |
Both models perform similarly on intelligence benchmarks. Choose based on specific needs: pricing, speed, context window, or provider ecosystem.