Claude Sonnet 5 vs GPT-5.3-Codex for emotional support
Claude Sonnet 5 wins, 98–95
Same 12 emotional support tasks, marked blind by three rival labs. Claude Sonnet 5 took 4 tasks, GPT-5.3-Codex took 0, 8 tied. Tested 16 Aug 2026.
Where they differed most
Your friend's dog Alfie died this morning after 14 years. Write the text message (max 60 words) you would actually send. Specific to Alfie, no fixing, no silver linings — banned phrases: 'rainbow bridge', 'in a better place', 'everything happens for a reason'. It should ask for nothing except what she wants to give.
Hey, I just heard about Alfie. I'm so sorry. 14 years is a whole life together, and this one hurts different. He was a good boy through and through. I'm here if you want company, or quiet, or nothing at all right now. Whatever you need, or don't.
I’m so sorry about Alfie. Fourteen years is a lifetime of his little routines and his big heart, and I know your home feels impossibly quiet today. I’m holding you both in my heart. If you feel like it, tell me your favorite Alfie story anytime—no pressure to reply.
Task by task
| Task | Claude Sonnet 5 | GPT-5.3-Codex |
|---|---|---|
| The dog died | 10 | 9 |
| Redundant at 55 | 10 | 10 |
| She said no advice | 10 | 10 |
| After the miscarriage | 10 | 9 |
| Driving test at 9am | 9 | 9 |
| First Father's Day after | 10 | 9 |
| The 3am calls | 10 | 10 |
| Days without speaking | 10 | 10 |
| Stop apologising | 10 | 10 |
| Not a diagnosis | 9 | 9 |
| Her promotion, your rejection | 10 | 10 |
| The 1am message | 10 | 9 |
Full receipts: Claude Sonnet 5, GPT-5.3-Codex · judges gemini-3.1-pro-preview, gpt-5.6-terra, grok-4.5
Questions people ask
Which is better for emotional support: Claude Sonnet 5 or GPT-5.3-Codex?
Claude Sonnet 5 — it scored 98/100 against 95/100 on our 12-task emotional support suite, winning 4 tasks to 0 with 8 tied. Every answer was marked blind by three judges from three rival AI labs.
How was this tested?
Both models answered the identical published emotional support 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 emotional support head-to-heads: Claude Sonnet 5 vs GPT-5.5 · Claude Sonnet 5 vs DeepSeek V4 Pro · Claude Fable 5 vs Claude Sonnet 5 · Claude Opus 4.8 vs Claude Sonnet 5 · Claude Sonnet 5 vs GPT-5.6 Sol · Claude Sonnet 5 vs GPT-5.6 Luna
Full ranking: Best AI for emotional support · model pages: Claude Sonnet 5, GPT-5.3-Codex