Claude 3.5 HaikuvsGPT-5.5-Pro
Claude 3.5 Haiku | GPT-5.5-Pro | |
|---|---|---|
| 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. | 50%Best | 36% |
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. | 40.6% | — |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 83% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 90.1% |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 57.2% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 52.4% |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 39.6% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 41.6% | — |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 82.3% |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Oct 22 2024 | Apr 23 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude 3.5 Haiku or GPT-5.5-Pro?
Claude 3.5 Haiku leads GPT-5.5-Pro on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3.5 Haiku shipped 548 days before GPT-5.5-Pro, 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 BullshitBench v2, Claude 3.5 Haiku leads at 50% vs GPT-5.5-Pro at 36%.
Frequently asked questions
Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.
GPT-5.5-Pro was released by OpenAI on Apr 23 2026.
Other comparisons
Claude 3.5 HaikuvsGemini 3.6 FlashGPT-5.5-ProvsGemini 3.6 FlashClaude 3.5 HaikuvsMuse Spark 1.2GPT-5.5-ProvsMuse Spark 1.2Claude 3.5 HaikuvsGrok 4.5GPT-5.5-ProvsGrok 4.5Claude 3.5 HaikuvsDeepSeek-V4-Flash-0731GPT-5.5-ProvsDeepSeek-V4-Flash-0731Claude 3.5 HaikuvsMistral Medium 3.5GPT-5.5-ProvsMistral Medium 3.5Claude 3.5 HaikuvsKimi K3GPT-5.5-ProvsKimi K3