Updated March 26, 2026· Based on independent benchmark data
Gemini 3 Flash Preview (Reasoning) and GPT-5 Codex (high) are virtually tied on intelligence (46.4 vs 44.6). Gemini 3 Flash Preview (Reasoning) is 2.5x cheaper at $0.50/1M tokens vs $1.25/1M.
| Metric | Gemini 3 Flash Preview (Reasoning) | GPT-5 Codex (high) |
|---|---|---|
| Intelligence Score | 46.4 | 44.6 |
| Coding Score | 42.6 | 38.9 |
| Math Score | 97.0 | 98.7 |
| Speed (tok/s) | 192 tok/s | 180 tok/s |
| Latency (TTFT) | 6.11s | 9.17s |
| Input Price / 1M tokens | $0.50 | $1.25 |
| Output Price / 1M tokens | $3.00 | $10 |
| Context Window |
Gemini 3 Flash Preview (Reasoning) and GPT-5 Codex (high) perform similarly on overall intelligence, scoring 46.4 and 44.6 respectively. For coding tasks, Gemini 3 Flash Preview (Reasoning) has the edge with a coding score of 42.6 vs 38.9. Both models show similar math performance (97.0 vs 98.7).
Both models deliver similar output speeds: Gemini 3 Flash Preview (Reasoning) at 192 tok/s and GPT-5 Codex (high) at 180 tok/s. Time to first token is 6.11s for Gemini 3 Flash Preview (Reasoning) vs 9.17s for GPT-5 Codex (high), which affects perceived responsiveness in interactive applications.
Gemini 3 Flash Preview (Reasoning) is more affordable at $0.50/1M input tokens ($3.00/1M output), while GPT-5 Codex (high) costs $1.25/1M input ($10/1M output). That makes GPT-5 Codex (high) 2.5x 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, Gemini 3 Flash Preview (Reasoning) would cost approximately $3.00/month vs $7.50/month for GPT-5 Codex (high) in input costs alone.
Choose Gemini 3 Flash Preview (Reasoning) when you need stronger coding performance (42.6), lower cost.
Gemini 3 Flash Preview (Reasoning) scores higher on coding benchmarks (42.6 vs 38.9), making it the better choice for programming tasks.
Gemini 3 Flash Preview (Reasoning) is cheaper at $0.50/1M input tokens vs $1.25/1M for GPT-5 Codex (high).
Gemini 3 Flash Preview (Reasoning) is faster, producing output at 192 tok/s compared to GPT-5 Codex (high)'s 180 tok/s.
No, Gemini 3 Flash Preview (Reasoning) does not support image input. Neither model supports image input.
Data last synced: March 26, 2026
| N/A |
| N/A |
| 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.