GPT-5.3-Codex vs GPT-5.6 Sol for creative writing
GPT-5.6 Sol wins, 97–94
Same 12 creative writing tasks, marked blind by three rival labs. GPT-5.6 Sol took 5 tasks, GPT-5.3-Codex took 1, 6 tied. Tested 16 Aug 2026.
Where they differed most
Write a story of exactly 100 words about a lost glove. No title — just the story. Count carefully: exactly 100.
At dusk, Mara found a single wool glove curled beside the bus stop bench, damp with mist and smelling faintly of cedar. She tucked it into her pocket, meaning to leave it at lost and found, but the night grew sharp, and her own fingers ached. On the walk home she wore the stranger’s glove on her left hand, feeling oddly accompanied. Weeks passed. No one claimed it. Then, during spring cleaning, she discovered a note stitched inside the cuff: If found, keep warm for me. She smiled, slipped it on, and whispered thanks to whoever had let go first.
At dawn, Mara found a single red glove beside the frozen pond. Its fingers pointed toward the reeds, as if asking her to follow. She did, stepping over silver grass, until she heard a faint whimper. Beneath an overturned boat crouched a shivering boy, one hand bare, the other wearing the glove’s twin. Mara wrapped him in her coat and led him home. Years later, the boy returned, carrying that red glove in a glass case. “You saved me,” he said. Mara smiled. “No,” she replied, “your glove did.” Outside, snow began falling, soft as feathers, coveri…
Task by task
| Task | GPT-5.3-Codex | GPT-5.6 Sol |
|---|---|---|
| The launderette at closing | 10 | 10 |
| Angry without saying angry | 10 | 10 |
| Ferry, retired | 10 | 10 |
| The piano argument | 9 | 10 |
| A hundred words exactly | 10 | 8 |
| Keep the voice | 9 | 10 |
| Kill the purple | 9 | 10 |
| His side of it | 9 | 9 |
| The bin lorry story | 10 | 10 |
| Around the hole | 9 | 10 |
| No one can promise Bridport | 8 | 9 |
| Refuse the fake article | 10 | 10 |
Full receipts: GPT-5.3-Codex, GPT-5.6 Sol · judges claude-sonnet-5, gemini-3.1-pro-preview, grok-4.5
Questions people ask
Which is better for creative writing: GPT-5.3-Codex or GPT-5.6 Sol?
GPT-5.6 Sol — it scored 97/100 against 94/100 on our 12-task creative writing suite, winning 5 tasks to 1 with 6 tied. Every answer was marked blind by three judges from three rival AI labs.
How was this tested?
Both models answered the identical published creative writing tasks. Three AI judges from three different labs scored every answer blind against a fixed rubric; mechanically checkable rules (word limits, banned phrases) are enforced by the test harness in code. The raw outputs and judge verdicts are downloadable.
More creative writing head-to-heads: GPT-5.5 vs GPT-5.6 Sol · GPT-5.3-Codex vs GPT-5.5 · GPT-5.6 Sol vs GPT-5.6 Terra · GPT-5.3-Codex vs GPT-5.6 Terra · Gemini 3.5 Flash vs GPT-5.6 Sol · GPT-5.6 Sol vs Qwen3.7 Max
Full ranking: Best AI for creative writing · model pages: GPT-5.3-Codex, GPT-5.6 Sol