Updated March 26, 2026· Based on independent benchmark data
Grok 4.20 Beta 0309 (Reasoning) leads in intelligence with a score of 48.5 vs 44.6. GPT-5 Codex (high) is 1.6x cheaper at $1.25/1M tokens vs $2.00/1M. For speed, Grok 4.20 Beta 0309 (Reasoning) wins at 246 tok/s vs 180 tok/s.
| Metric | Grok 4.20 Beta 0309 (Reasoning) | GPT-5 Codex (high) |
|---|---|---|
| Intelligence Score | 48.5 | 44.6 |
| Coding Score | 42.2 | 38.9 |
| Math Score | N/A | 98.7 |
| Speed (tok/s) | 246 tok/s | 180 tok/s |
| Latency (TTFT) | 11.75s | 9.17s |
| Input Price / 1M tokens | $2.00 | $1.25 |
| Output Price / 1M tokens | $6.00 | $10 |
| Context Window | N/A |
Grok 4.20 Beta 0309 (Reasoning) outperforms GPT-5 Codex (high) on the intelligence index with a score of 48.5 compared to 44.6. For coding tasks, Grok 4.20 Beta 0309 (Reasoning) has the edge with a coding score of 42.2 vs 38.9.
Grok 4.20 Beta 0309 (Reasoning) generates output significantly faster at 246 tok/s compared to GPT-5 Codex (high)'s 180 tok/s, making it 1.4x faster for streaming responses. Time to first token is 9.17s for GPT-5 Codex (high) vs 11.75s for Grok 4.20 Beta 0309 (Reasoning), which affects perceived responsiveness in interactive applications.
GPT-5 Codex (high) is more affordable at $1.25/1M input tokens ($10/1M output), while Grok 4.20 Beta 0309 (Reasoning) costs $2.00/1M input ($6.00/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, Grok 4.20 Beta 0309 (Reasoning) would cost approximately $12.00/month vs $7.50/month for GPT-5 Codex (high) in input costs alone.
Choose Grok 4.20 Beta 0309 (Reasoning) when you need higher intelligence (48.5), stronger coding performance (42.2), faster output (246 tok/s). Choose GPT-5 Codex (high) when you need lower cost.
Grok 4.20 Beta 0309 (Reasoning) scores higher on coding benchmarks (42.2 vs 38.9), making it the better choice for programming tasks.
GPT-5 Codex (high) is cheaper at $1.25/1M input tokens vs $2.00/1M for Grok 4.20 Beta 0309 (Reasoning).
Grok 4.20 Beta 0309 (Reasoning) is faster, producing output at 246 tok/s compared to GPT-5 Codex (high)'s 180 tok/s.
No, Grok 4.20 Beta 0309 (Reasoning) 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. Grok 4.20 Beta 0309 (Reasoning) scores higher on intelligence (48.5), but GPT-5 Codex (high) may be better for specific use cases like budget-conscious projects or speed-critical applications.