// head_to_head
Gemini 3.5 Flash vs GPT-5.1-Codex-Max
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Gemini 3.5 Flash and GPT-5.1-Codex-Max are priced within ~10% of each other.
GPT-5.1-Codex-Max does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Gemini 3.5 Flash
- Blended / 1M
- $3.38
- Context
- 1.0M
- Released
- May 19, 2026
- Overall score
- 74.6
openai
GPT-5.1-Codex-Max
- Blended / 1M
- $3.44
- Context
- 400K
- Released
- Dec 4, 2025
- Overall score
- Not evaluated
Specs and pricing
| Metric | Gemini 3.5 Flash | GPT-5.1-Codex-Max |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 74.6 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.1357 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $3.38 | $3.44 |
| Input price / 1M | $1.50 | $1.25win |
| Output price / 1M | $9.00win | $10.00 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.150 | $0.125win |
| Context window | 1.0Mwin | 400K |
| Max output tokens | 66K | 128Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Gemini 3.5 Flash on top, GPT-5.1-Codex-Max below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Gemini 3.5 Flash | GPT-5.1-Codex-Max |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $982.80/mo | $1,019/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,200/mo | $1,150/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,164/mo | $1,170/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,108/mo | $1,944/mo |
| Bulk classification 500 in / 20 out × 5M requests | $3,975/mo | $3,563/mo |
Which should you pick?
You need to fit large documents in one call
Gemini 3.5 Flash
Wider context window — 1.0M against 400K.
Gemini 3.5 Flash vs GPT-5.1-Codex-Max FAQ
Which is better, Gemini 3.5 Flash or GPT-5.1-Codex-Max?
Gemini 3.5 Flash and GPT-5.1-Codex-Max are priced within ~10% of each other. GPT-5.1-Codex-Max does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Gemini 3.5 Flash cheaper than GPT-5.1-Codex-Max?
They cost about the same. Both land near $3.38 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.
Does Gemini 3.5 Flash or GPT-5.1-Codex-Max have a bigger context window?
Gemini 3.5 Flash has the larger context window: 1.0M for Gemini 3.5 Flash against 400K for GPT-5.1-Codex-Max. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Gemini 3.5 Flash and GPT-5.1-Codex-Max support prompt caching?
Both publish a cached-input rate: $0.150 per million for Gemini 3.5 Flash and $0.125 for GPT-5.1-Codex-Max, against full input rates of $1.50 and $1.25. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.