Claude 3 HaikuvsGPT-5.4
Claude 3 Haiku | GPT-5.4 | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $2.50 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $15.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.25 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.25Amazon Bedrock | $2.50Azure |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.25Amazon Bedrock | $15.00Azure |
| Benchmarks | ||
BullshitBench v2Nonsense detection — Given 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. | 10% | 48% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 33.3% | 92.8% |
| BenchmarksPublished by one model only | ||
Next.js EvalsNext.js coding — Vercel'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. | — | 77% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 75.1% |
Expert-SWE (Internal)Software engineering — OpenAI's private set of expert-level software-engineering problems. Higher is better. | — | 68.5% |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | — | 54.6% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 82.7% |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | — | 79% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity'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. | — | 52.1% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 73.95% |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 47.6% |
FrontierMath · Tier 4Advanced math — Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 27.1% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 75% |
GDPval (win/tie rate)Knowledge work — How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 83% |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Mar 4 2024 | Mar 5 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Claude 3 HaikuvsGemini 3.8 FlashGPT-5.4vsGemini 3.8 FlashClaude 3 HaikuvsMuse Spark 1.3GPT-5.4vsMuse Spark 1.3Claude 3 HaikuvsGrok 4.6GPT-5.4vsGrok 4.6Claude 3 HaikuvsDeepSeek-V4-Pro-0813GPT-5.4vsDeepSeek-V4-Pro-0813Claude 3 HaikuvsMistral Medium 3.5GPT-5.4vsMistral Medium 3.5Claude 3 HaikuvsKimi K3GPT-5.4vsKimi K3
Frequently asked questions
GPT-5.4 leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Only GPT-5.4 has a verified first-party API price: $2.50 per million input tokens and $15.00 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3 Haiku. Claude 3 Haiku shipped 731 days before GPT-5.4, 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, GPT-5.4 leads at 48% vs Claude 3 Haiku at 10%. On GPQA Diamond, GPT-5.4 leads at 92.8% vs Claude 3 Haiku at 33.3%.