Gemini 3.0 ProvsGPT-5-Codex
Gemini 3.0 Pro | GPT-5-Codex | |
|---|---|---|
| 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. | 48% | 39% |
| BenchmarksPublished by one model only | ||
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. | 76.2% | — |
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. | 52% | — |
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. | 31.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
| Overview | ||
| Company | OpenAI | |
| Release date | Nov 18 2025 | Sep 15 2025 |
| Access | Proprietary | Proprietary |
Other comparisons
Gemini 3.0 ProvsClaude Opus 5.5GPT-5-CodexvsClaude Opus 5.5Gemini 3.0 ProvsMuse Spark 1.3GPT-5-CodexvsMuse Spark 1.3Gemini 3.0 ProvsGrok 4.7GPT-5-CodexvsGrok 4.7Gemini 3.0 ProvsDeepSeek-V4.1-FlashGPT-5-CodexvsDeepSeek-V4.1-FlashGemini 3.0 ProvsMistral Medium 3.5GPT-5-CodexvsMistral Medium 3.5Gemini 3.0 ProvsKimi K3GPT-5-CodexvsKimi K3
Frequently asked questions
Gemini 3.0 Pro leads GPT-5-Codex on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5-Codex shipped 64 days before Gemini 3.0 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, Gemini 3.0 Pro leads at 48% vs GPT-5-Codex at 39%.