GPT-5 is a top-tier frontier AI model, developed by OpenAI and released in 2025-08. It is best known for real-world software engineering performance, scoring 74.9% on SWE-bench Verified.

Is GPT-5 available as an open-weight model?

GPT-5 is a proprietary closed-weight model. Its weights are not publicly available — access is through the OpenAI API only.

What benchmarks has GPT-5 been evaluated on?

GPT-5 has been evaluated on: SWE-bench Verified (74.9%), GPQA Diamond (88.4%). Scores tagged SR are self-reported by the provider; scores tagged 3P or AA have been independently verified by third parties.

Is GPT-5 available in FlowHunt?

Yes — GPT-5 is directly available in FlowHunt. You can use it to build AI agents, automated workflows, chatbots, and document processing pipelines without any additional setup.

How does GPT-5 compare to other AI models?

You can compare GPT-5 against all 24 models tracked on the FlowHunt AI Leaderboard using the sortable benchmark table. The Benchmark Rankings section on this page shows GPT-5's position on each benchmark it has been evaluated on.

OpenAI

GPT-5

FrontierAvailable in FlowHunt

Try in FlowHunt

GPT-5 is a top-tier frontier AI model, developed by OpenAI and released in August 2025. It is a proprietary closed-weight model, available through the OpenAI API. It supports a 400K-token context window, adequate for most documents and multi-turn applications.

On the FlowHunt AI Leaderboard it is one of 24 tracked models, evaluated across 2 benchmarks. Standout scores: 88.4% on GPQA Diamond (#7 of 14); 74.9% on SWE-bench Verified (#10 of 13).

GPT-5 was released on August 7, 2025 as OpenAI’s first model to self-report above-human performance on several hard reasoning benchmarks. It was the first GPT to integrate text, image, and audio input as a unified capability at the reasoning level rather than through a pipeline of specialised models. GPT-5 set the foundation for the current frontier tier: its 400K context window was, at release, the longest available from OpenAI; its coding improvement over GPT-4o was significant enough to displace a large portion of Codex-based and GPT-4o-based development tooling. The launch drove the fastest acceleration in GPT API adoption since ChatGPT’s debut in 2022.

Note: Unified model replacing GPT-4o, o3, o4-mini, GPT-4.1. AIME 2025: 94.6%.

Try in FlowHunt

Released: August 2025
Context: 400K tokens
Weights: Closed
Tier: Frontier
Provider: OpenAI

GPT-5 Benchmark Rankings

Rank among all 24 models tracked on this leaderboard. SR = self-reported · 3P / AA / C = independently verified.

Benchmark	Score	Rank	Source	What it measures
SWE-bench Verified	74.9%	10 of 13	SR	Real GitHub issue resolution (500 verified issues)
GPQA Diamond	88.4%	7 of 14	SR	Graduate-level Google-proof science Q&A

Detailed Benchmark Scores

SWE-V SR

74.9%

Real GitHub issue resolution (500 verified issues)

GPQA ◇ SR

88.4%

Graduate-level Google-proof science Q&A

GPT-5 vs. Frontier Peers

Head-to-head benchmark comparison with other Frontier-tier models. Higher is better for all metrics.

Benchmark	GPT-5	Claude Opus 4.8	Claude Opus 4.7
SWE-V	74.9%	88.6%	87.6%
GPQA ◇	88.4%	93.6%	94.2%

About OpenAI

OpenAI Founded 2015 · San Francisco, CA

Website →

OpenAI was founded in December 2015 as a nonprofit AI research laboratory by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, John Schulman, and Wojciech Zaremba, with the mission of developing artificial general intelligence (AGI) that benefits all of humanity. In 2019 it created a capped-profit subsidiary, OpenAI LP, to raise institutional capital and scale model training. The company is known for the GPT series of language models (GPT-1 through GPT-5.5), the DALL-E image generation series, Whisper speech recognition, and Sora video generation. OpenAI operates the ChatGPT consumer application, a developer API, and enterprise services through Microsoft Azure. As of 2026 it maintains a close strategic partnership with Microsoft, which is the company's largest investor and cloud provider.

Use Cases

What to Use GPT-5 For

Software Engineering: GPT-5 achieves 74% on SWE-bench Verified — ranked #10 of 13 models tracked here. It handles code generation, bug fixing, and code review for typical development tasks, though frontier models score significantly higher on fully autonomous complex engineering.
Scientific & Technical Reasoning: GPT-5 scores 88% on GPQA Diamond (#7 of 14 models), around or above the human PhD-expert baseline. It handles demanding scientific reasoning, research literature summarisation, and knowledge-intensive tasks across STEM disciplines.

Strengths & Limitations

Strengths

Solid coding assistance — 74% SWE-bench Verified
Advanced scientific Q&A — 88% GPQA Diamond
Long-context tasks (400K context window)

Limitations

Closed-weight — cannot be self-hosted or fine-tuned on private data

More to Compare

Related AI Models

Browse the Full AI Model Leaderboard

Compare all 24 models across 11 benchmarks — sortable, sourced, and updated June 2026.

← Back to AI Leaderboard Try in FlowHunt

Frequently asked questions

: GPT-5 is a top-tier frontier AI model, developed by OpenAI and released in 2025-08. It is best known for real-world software engineering performance, scoring 74.9% on SWE-bench Verified.
: GPT-5 is a proprietary closed-weight model. Its weights are not publicly available — access is through the OpenAI API only.
: GPT-5 supports a 400K-token context window, adequate for most documents and multi-turn applications.
: GPT-5 has been evaluated on: SWE-bench Verified (74.9%), GPQA Diamond (88.4%). Scores tagged SR are self-reported by the provider; scores tagged 3P or AA have been independently verified by third parties.
: Yes — GPT-5 is directly available in FlowHunt. You can use it to build AI agents, automated workflows, chatbots, and document processing pipelines without any additional setup.
: You can compare GPT-5 against all 24 models tracked on the FlowHunt AI Leaderboard using the sortable benchmark table. The Benchmark Rankings section on this page shows GPT-5's position on each benchmark it has been evaluated on.

Learn more

GPT-5.5 — Benchmarks, Capabilities, and Use Cases

GPT-5.5 is a proprietary AI model from OpenAI, classified as Frontier tier with a 1M tokens context window. It is available directly in FlowHunt. Explore benchm...

Apr 23, 2026 4 min read

GPT-5.4 — Benchmarks, Capabilities, and Use Cases

GPT-5.4 is a proprietary AI model from OpenAI, classified as Frontier tier with a 1M tokens context window. It is available directly in FlowHunt. Explore benchm...

Mar 5, 2026 3 min read