Gemini 3.5 FlashvsGPT-5.3-Codex
Gemini 3.5 Flash | 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. | $1.50 | $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. | $9.00 | $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. | $0.15 | $0.175 |
| 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. | 20% | 24% |
Arena Elo (Code)Community preference (code) — Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1499 | 1406 |
| BenchmarksPublished by one model only | ||
Gray Swan IPI · k = 1Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 14.1% | — |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 54.2% | — |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 60.5% | — |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 55.1% | — |
CursorBench v3.2Agentic coding — Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 48.8% | — |
CursorBench v3.1Agentic coding — Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 49.8% | — |
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. | 37% | — |
MLE-BenchML engineering — Can the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better. | 49.7% | — |
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. | — | 83% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 76.2% | — |
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. | 83.6% | — |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 56.5% | — |
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. | 58% | — |
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. | 40.2% | — |
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. | 72.1% | — |
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. | 78.4% | — |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 57.9% | — |
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. | 1656 | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1349 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 84.2% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 83.6% | — |
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 33.6% | — |
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. | 77.3% | — |
MRCR v2 (8-needle) · 1M pointwiseLong context — Tests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | 26.6% | — |
Arena Elo (Text)Community preference — Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1476 | — |
| Overview | ||
| Company | OpenAI | |
| Release date | May 19 2026 | Feb 5 2026 |
| Access | Proprietary | Proprietary |
Which is better: Gemini 3.5 Flash or GPT-5.3-Codex?
Gemini 3.5 Flash and GPT-5.3-Codex are evenly matched across the 2 benchmarks they both report (BullshitBench v2, Arena Elo (Code)). Gemini 3.5 Flash is cheaper on both input and output: $1.50 vs $1.75 per million input tokens, and $9.00 vs $14.00 per million output tokens. GPT-5.3-Codex shipped 103 days before Gemini 3.5 Flash, 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-5.3-Codex leads at 24% vs Gemini 3.5 Flash at 20%. On Arena Elo (Code), Gemini 3.5 Flash leads at 1499 vs GPT-5.3-Codex at 1406.
Frequently asked questions
Gemini 3.5 Flash was released by Google on May 19 2026.
GPT-5.3-Codex was released by OpenAI on Feb 5 2026.
Gemini 3.5 Flash is cheaper on both input and output: $1.50 vs $1.75 per million input tokens, and $9.00 vs $14.00 per million output tokens. Rates are pay-as-you-go API prices verified on August 18, 2026.
Other comparisons
Gemini 3.5 FlashvsClaude Opus 5GPT-5.3-CodexvsClaude Opus 5Gemini 3.5 FlashvsMuse GlimmerGPT-5.3-CodexvsMuse GlimmerGemini 3.5 FlashvsGrok 4.6GPT-5.3-CodexvsGrok 4.6Gemini 3.5 FlashvsDeepSeek-V4-Pro-0813GPT-5.3-CodexvsDeepSeek-V4-Pro-0813Gemini 3.5 FlashvsMistral Medium 3.5GPT-5.3-CodexvsMistral Medium 3.5Gemini 3.5 FlashvsKimi K3GPT-5.3-CodexvsKimi K3