MiniMax M2 is the newer model, released after GPT-5 Codex.
| Spec | GPT-5 Codex | MiniMax M2 |
|---|---|---|
| Input price | — | Free |
| Output price | — | Free |
| Context window | — | 205K tokens |
| Released | Sep 2025 | Oct 2025 |
| SWE-bench Verified | 74.5% | 69.4% |
Not enough votes to call it. On the specs, GPT-5 Codex has the edge: bigger model tier, major provider backing.
MiniMax M2 uses 3.1x more transitions
MiniMax M2 is the newer model, released after GPT-5 Codex.
| Spec | GPT-5 Codex | MiniMax M2 |
|---|---|---|
| Input price | — | Free |
| Output price | — | Free |
| Context window | — | 205K tokens |
| Released | Sep 2025 | Oct 2025 |
| SWE-bench Verified | 74.5% | 69.4% |
Not enough votes to call it. On the specs, GPT-5 Codex has the edge: bigger model tier, major provider backing.
MiniMax M2 uses 3.1x more transitions