ModelRefs / GPT-5 vs GPT-5 Mini — Benchmarks, Pricing & Coding Comparis…
GPT-5 vs GPT-5 Mini — Benchmarks, Pricing & Coding Comparis…
GPT-5 vs GPT-5 Mini: side-by-side benchmarks, pricing, context windows, coding ability and deployment. Pick the right model for your stack.
Overview
GPT-5: GPT-5 is OpenAI's August 2025 reasoning model for coding, reasoning, and agentic tasks. The API model supports text input and output, image input, configurable reasoning effort, and an immutable gpt-5-2025-08-07 snapshot; OpenAI now classifies it as a previous-generation model.
GPT-5 Mini: GPT-5 Mini is OpenAI's August 2025 cost-efficient reasoning model for well-defined, latency-sensitive, and high-volume workloads. The API model supports text input and output, image input, configurable reasoning effort, and an immutable gpt-5-mini-2025-08-07 snapshot; OpenAI now classifies it as a previous-generation model.
Context window: GPT-5 accepts up to 400,000 tokens, GPT-5 Mini up to 400,000. Confirm the limit for your specific deployment channel before relying on it.
GPT-5 vs GPT-5 Mini at a glance
| Attribute | GPT-5 | GPT-5 Mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Released | 2025-08-07 | 2025-08-07 |
| Context window | 400,000 tokens | 400,000 tokens |
| Input price | $1.25/M tokens | $0.25/M tokens |
| Output price | $10/M tokens | $2/M tokens |
| Licence | Proprietary | Proprietary |
| Self-hostable | No, hosted only | No, hosted only |
| Modalities | text, vision | text, vision |
Benchmarks reported for both
| Benchmark | GPT-5 | GPT-5 Mini | Reported |
|---|---|---|---|
| aider-polyglot | 88 | 71.6 | 2025-08-07 |
| aime-2025 | 94.6 | 91.1 | 2025-08-07 |
| browsecomp-long-context | 90 | 89.4 | 2025-08-07 |
| gpqa | 85.7 | 82.3 | 2025-08-07 |
| longfact-concepts | 1 | 0.7 | 2025-08-07 |
| swe-bench | 74.9 | 71 | 2025-08-07 |
| tau-bench | 96.7 | 74.1 | 2025-08-07 |
Scores are as published by their cited sources on the dates shown. Different runs use different harnesses, prompts, and dates, so treat these as directional evidence rather than a head-to-head result.
Where they differ most
- Cost Efficiency: GPT-5 47%, GPT-5 Mini 78%. GPT-5 Mini leads on this dimension.
- Tool Use: GPT-5 97%, GPT-5 Mini 74%. GPT-5 leads on this dimension.
- Instruction Following: GPT-5 88%, GPT-5 Mini 72%. GPT-5 leads on this dimension.
- Agentic: GPT-5 89%, GPT-5 Mini 73%. GPT-5 leads on this dimension.
- Coding: GPT-5 81%, GPT-5 Mini 71%. GPT-5 leads on this dimension.
- Reasoning: GPT-5 90%, GPT-5 Mini 87%. GPT-5 leads on this dimension.
Capability scores are ModelRefs' own derived signals, not vendor claims or benchmark results. Validate against your own workload before relying on them.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to GPT-5 vs GPT-5 Mini — Benchmarks, Pricing & Coding Comparis….
Frequently asked questions
Which is better, GPT-5 or GPT-5 Mini?
GPT-5 and GPT-5 Mini target different workloads — see the benchmark and pricing tables for a side-by-side answer.
Is GPT-5 cheaper than GPT-5 Mini?
Compare $0.00125 vs $0.00025 on this page.