Claude 3.5 Sonnet (upgraded)vsGPT-5.2
Claude 3.5 Sonnet (upgraded) | GPT-5.2 | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 38% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 49% | 80%Best |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 52.9% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 92.4% |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | — | 1476 |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1419 |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Oct 22 2024 | Dec 11 2025 |
| Access | Proprietary | Proprietary |
Which is better: Claude 3.5 Sonnet (upgraded) or GPT-5.2?
GPT-5.2 leads Claude 3.5 Sonnet (upgraded) on 1 of the 1 benchmark they both report (SWE-Bench Verified). Claude 3.5 Sonnet (upgraded) shipped 415 days before GPT-5.2, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On SWE-Bench Verified, GPT-5.2 leads at 80% vs Claude 3.5 Sonnet (upgraded) at 49%.
Frequently asked questions
Claude 3.5 Sonnet (upgraded) was released by Anthropic on Oct 22 2024.
GPT-5.2 was released by OpenAI on Dec 11 2025.
GPT-5.2 leads on SWE-Bench Verified — Claude 3.5 Sonnet (upgraded) 49% vs GPT-5.2 80%.
Other comparisons
Claude 3.5 Sonnet (upgraded)vsGemini 3.6 FlashGPT-5.2vsGemini 3.6 FlashClaude 3.5 Sonnet (upgraded)vsMuse Spark 1.2GPT-5.2vsMuse Spark 1.2Claude 3.5 Sonnet (upgraded)vsGrok 4.5GPT-5.2vsGrok 4.5Claude 3.5 Sonnet (upgraded)vsDeepSeek-V4-Flash-0731GPT-5.2vsDeepSeek-V4-Flash-0731Claude 3.5 Sonnet (upgraded)vsMistral Medium 3.5GPT-5.2vsMistral Medium 3.5Claude 3.5 Sonnet (upgraded)vsKimi K3GPT-5.2vsKimi K3