GPT-5.6 Luna has a larger context window than Qwen3 235B A22B (1.1M tokens vs 33K tokens).
| Spec | GPT-5.6 Luna | Qwen3 235B A22B |
|---|---|---|
| Input price | $1/M tokens | — |
| Output price | $6/M tokens | — |
| Context window | 1.1M tokens | 33K tokens |
| Released | Jul 2026 | Apr 2025 |
Not enough votes to call it. On the specs, nothing separates them.
GPT-5.6 Luna uses 83.6x more hedging
GPT-5.6 Luna has a larger context window than Qwen3 235B A22B (1.1M tokens vs 33K tokens).
| Spec | GPT-5.6 Luna | Qwen3 235B A22B |
|---|---|---|
| Input price | $1/M tokens | — |
| Output price | $6/M tokens | — |
| Context window | 1.1M tokens | 33K tokens |
| Released | Jul 2026 | Apr 2025 |
Not enough votes to call it. On the specs, nothing separates them.
GPT-5.6 Luna uses 83.6x more hedging