Updated March 26, 2026· Based on independent benchmark data
GPT-5.3 Codex (xhigh) leads in intelligence with a score of 54.0 vs 32.8. Mercury 2 is 7.0x cheaper at $0.25/1M tokens vs $1.75/1M. For speed, Mercury 2 wins at 894 tok/s vs 72 tok/s.
| Metric | Mercury 2 | GPT-5.3 Codex (xhigh) |
|---|---|---|
| Intelligence Score | 32.8 | 54.0 |
| Coding Score | 30.6 | 53.1 |
| Math Score | N/A | N/A |
| Speed (tok/s) | 894 tok/s | 72 tok/s |
| Latency (TTFT) | 3.81s | 83.91s |
| Input Price / 1M tokens | $0.25 | $1.75 |
| Output Price / 1M tokens | $0.75 | $14 |
| Context Window | 128K |
GPT-5.3 Codex (xhigh) outperforms Mercury 2 on the intelligence index with a score of 54.0 compared to 32.8. For coding tasks, GPT-5.3 Codex (xhigh) has the edge with a coding score of 53.1 vs 30.6.
Mercury 2 generates output significantly faster at 894 tok/s compared to GPT-5.3 Codex (xhigh)'s 72 tok/s, making it 12.4x faster for streaming responses. Time to first token is 3.81s for Mercury 2 vs 83.91s for GPT-5.3 Codex (xhigh), which affects perceived responsiveness in interactive applications.
Mercury 2 is more affordable at $0.25/1M input tokens ($0.75/1M output), while GPT-5.3 Codex (xhigh) costs $1.75/1M input ($14/1M output). That makes GPT-5.3 Codex (xhigh) 7.0x more expensive per token, which can add up significantly at scale. For a typical workload of 100 requests per day at 2,000 tokens each, Mercury 2 would cost approximately $1.50/month vs $10.50/month for GPT-5.3 Codex (xhigh) in input costs alone.
Choose Mercury 2 when you need faster output (894 tok/s), lower cost. Choose GPT-5.3 Codex (xhigh) when you need higher intelligence (54.0), stronger coding performance (53.1).
GPT-5.3 Codex (xhigh) scores higher on coding benchmarks (53.1 vs 30.6), making it the better choice for programming tasks.
Mercury 2 is cheaper at $0.25/1M input tokens vs $1.75/1M for GPT-5.3 Codex (xhigh).
Mercury 2 is faster, producing output at 894 tok/s compared to GPT-5.3 Codex (xhigh)'s 72 tok/s.
No, Mercury 2 does not support image input. Neither model supports image input.
Data last synced: March 26, 2026
| N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
| Output Modalities | Text | Text |
| Free Tier | No | No |
It depends on your priorities. GPT-5.3 Codex (xhigh) scores higher on intelligence (54.0), but Mercury 2 may be better for specific use cases like budget-conscious projects or speed-critical applications.