Compare AI models
| 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. | 34% | 39% |
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. | 72.5% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 79.6% | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | May 22 2025 | Sep 15 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Opus 4vsGemini 4 ArgonGPT-5-CodexvsGemini 4 ArgonClaude Opus 4vsMuse WonderGPT-5-CodexvsMuse WonderClaude Opus 4vsGrok 4.7GPT-5-CodexvsGrok 4.7Claude Opus 4vsDeepSeek-V4.1-FlashGPT-5-CodexvsDeepSeek-V4.1-FlashClaude Opus 4vsMistral Large 4GPT-5-CodexvsMistral Large 4Claude Opus 4vsKimi K3GPT-5-CodexvsKimi K3Frequently asked questions
GPT-5-Codex leads Claude Opus 4 on 1 of the 1 benchmark they both report (BullshitBench v2). Claude Opus 4 shipped 116 days before GPT-5-Codex, 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-Codex leads at 39% vs Claude Opus 4 at 34%.