Compare AI models
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| 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. | $3.00 | $10.00 |
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 | $30.00 |
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. | $0.30 | — |
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. | $3.00Amazon Bedrock | $10.00OpenAI |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $15.00Amazon Bedrock | $30.00OpenAI |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 83.4% | 42.5% |
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. | 79% | — |
SWE-Bench VerifiedCoding — Real 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. | 77.2% | — |
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. | 39% | — |
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. | 13.6% | — |
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. | 61.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Sep 29 2025 | Nov 6 2023 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Sonnet 4.5vsGemini 4 ArgonGPT-4 TurbovsGemini 4 ArgonClaude Sonnet 4.5vsMuse Spark 1.3GPT-4 TurbovsMuse Spark 1.3Claude Sonnet 4.5vsGrok 4.7GPT-4 TurbovsGrok 4.7Claude Sonnet 4.5vsDeepSeek-V4.1-FlashGPT-4 TurbovsDeepSeek-V4.1-FlashClaude Sonnet 4.5vsMistral Large 4GPT-4 TurbovsMistral Large 4Claude Sonnet 4.5vsKimi K3GPT-4 TurbovsKimi K3Frequently asked questions
Claude Sonnet 4.5 leads GPT-4 Turbo on 1 of the 1 benchmark they both report (GPQA Diamond). Claude Sonnet 4.5 is cheaper on both input and output: $3.00 vs $10.00 per million input tokens, and $15.00 vs $30.00 per million output tokens. GPT-4 Turbo shipped 693 days before Claude Sonnet 4.5, 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 GPQA Diamond, Claude Sonnet 4.5 leads at 83.4% vs GPT-4 Turbo at 42.5%.