← comparisons · head to head
GPT-5.6 vs Claude Sonnet 5
GPT-5.6 scores higher than Claude Sonnet 5 on all 5 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, GPT-5.6 is at 70.2 and Claude Sonnet 5 at 36.7 (out of 100).
Scores as published by each board; table composed September 25, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | GPT-5.6 | Claude Sonnet 5 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,617.1 | 1,538.2 | GPT-5.6 |
| LiveBench global average (0-100) | 81.1 | 76 | GPT-5.6 |
| SimpleBench AVG@5 % (private set) | 71.7 | 60.6 | GPT-5.6 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 63.7 | 59.6 | GPT-5.6 |
| Artificial Analysis intelligence index · measured runs only | 47 | 38.2 | GPT-5.6 |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
GPT-5.6 at a glance
- Developer
- OpenAI
- Status
- Live since July 9, 2026
- API price
- $4 input / $20 output per 1M tokens · OpenAI, gpt-5.6
- Context window
- 1.05M tokens
Live — Sol · Terra · Luna since Jul 9 · repriced Jul 30: Luna −80%, Terra −20%.
Three ChatGPT leaks in five hours were one release note — and the line none of them quoted is the real change
2026-08-06 · Three separate leaks landed in five hours claiming three separate ChatGPT changes: an upgraded GPT-5.6 Sol for Plus and Pro, a new reasoning slider rolling out, and unlimited chats coming for free users. All three are real.
OpenAI cut Luna 80% — Azure kept the old price, so Luna costs 5× more on Azure than direct
2026-08-04 · OpenAI cut GPT-5.6 Luna by 80% on July 30. We covered it. What we did not check — and should have, because it is the number that actually lands on a bill — is whether the clouds passed it on.
Claude Sonnet 5 at a glance
- Developer
- Anthropic
- Status
- Live since June 30, 2026
- API price
- $2 input / $10 output per 1M tokens · Anthropic, claude-sonnet-5
- Context window
- 1M tokens
Shipped Jun 30.
GPT-5.6 vs Claude Sonnet 5: quick answers
Which is better, GPT-5.6 or Claude Sonnet 5?
It depends on what you measure. GPT-5.6 scores higher than Claude Sonnet 5 on all 5 public leaderboards that rate both. GPT-5.6's widest lead is on LiveBench. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, GPT-5.6 is at 70.2 and Claude Sonnet 5 at 36.7 (out of 100).
Which is newer, GPT-5.6 or Claude Sonnet 5?
GPT-5.6. It went live on July 9, 2026, 9 days after Claude Sonnet 5 (June 30, 2026).
Which is cheaper, GPT-5.6 or Claude Sonnet 5?
Claude Sonnet 5 is cheaper on both input and output. On each vendor's own API, GPT-5.6 is $4 input / $20 output per million tokens and Claude Sonnet 5 is $2 input / $10 output per million tokens. GPT-5.6's rate rises for prompts over 272K tokens. Prices as published in the models.dev catalog, as of 2026-09-25.
Which has the bigger context window, GPT-5.6 or Claude Sonnet 5?
GPT-5.6, at 1.05M tokens against Claude Sonnet 5's 1M, as each vendor lists it.
Who makes GPT-5.6 and Claude Sonnet 5?
GPT-5.6 is from OpenAI; Claude Sonnet 5 is from Anthropic.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 25, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear the minute the next one drops. Free.
A free Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Texts or a phone call on paid plans.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire