Claude Sonnet 4.6vsGPT-5.3-Codex
Claude Sonnet 4.6 | GPT-5.3-Codex | |
|---|---|---|
| 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 | $1.75 |
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 | $14.00 |
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 | $0.175 |
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 | $1.75Azure |
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 | $14.00Azure |
| 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. | 91% | 24% |
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. | 79.6% | 85% |
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. | 54% | 81% |
| BenchmarksPublished by one model only | ||
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 30% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 69.5% | — |
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 62% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 33.2% | — |
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. | 58.3% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 89.9% | — |
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. | 72.5% | — |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 51% | — |
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1676 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 72.4% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 74.5% | — |
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 6.7% | — |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | 84.9% | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Feb 17 2026 | Feb 5 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Claude Sonnet 4.6vsGemini 3.7 FlashGPT-5.3-CodexvsGemini 3.7 FlashClaude Sonnet 4.6vsMuse GlimmerGPT-5.3-CodexvsMuse GlimmerClaude Sonnet 4.6vsGrok 4.6GPT-5.3-CodexvsGrok 4.6Claude Sonnet 4.6vsDeepSeek-V4-Pro-0813GPT-5.3-CodexvsDeepSeek-V4-Pro-0813Claude Sonnet 4.6vsMistral Medium 3.5GPT-5.3-CodexvsMistral Medium 3.5Claude Sonnet 4.6vsKimi K3GPT-5.3-CodexvsKimi K3
Frequently asked questions
GPT-5.3-Codex leads Claude Sonnet 4.6 on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, Next.js Evals). GPT-5.3-Codex is cheaper on both input and output: $1.75 vs $3.00 per million input tokens, and $14.00 vs $15.00 per million output tokens. GPT-5.3-Codex shipped 12 days before Claude Sonnet 4.6, 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 Sonnet 4.6 leads at 91% vs GPT-5.3-Codex at 24%. On SWE-Bench Verified, GPT-5.3-Codex leads at 85% vs Claude Sonnet 4.6 at 79.6%. On Next.js Evals, GPT-5.3-Codex leads at 81% vs Claude Sonnet 4.6 at 54%.
Claude Sonnet 4.6 was released by Anthropic on Feb 17 2026.
GPT-5.3-Codex was released by OpenAI on Feb 5 2026.
GPT-5.3-Codex leads on SWE-Bench Verified — Claude Sonnet 4.6 79.6% vs GPT-5.3-Codex 85%.
GPT-5.3-Codex is cheaper on both input and output: $1.75 vs $3.00 per million input tokens, and $14.00 vs $15.00 per million output tokens. Rates are pay-as-you-go API prices verified on August 18, 2026.