GPT-5

GA

by OpenAI · GPT-5 family · best for legacy flagship on a migration path

ReasoningCodingMultimodal
6.5
AI Panel Score
Value 7.0/10

GPT-5 is OpenAI's original unified reasoning flagship, released 2025-08-07 — the first single SKU with a configurable reasoning effort dial (minimal/low/medium/high) and the model that established the 400K context standard for the family. It set state-of-the-art at launch on AIME 2025 (94.6% no tools), SWE-bench Verified (74.9%), Aider Polyglot (88%), and MMMU (84.2%). It remains GA and attractively priced at $1.25/$10, but a 2024-09 knowledge cutoff and the newer GPT-5.4/5.5 generation make it a legacy choice. The one-sentence buyer's take: a strong model now firmly in the migration lane — fine for in-flight builds, wrong for new ones.

What's new

  • GPT-5 was the original release that established the unified reasoning model — a single SKU with configurable reasoning effort (minimal/low/medium/high) replacing the prior o-series/chat split. It set state of the art at launch on AIME 2025 (94.6% without tools), SWE-bench Verified (74.9%), Aider Polyglot (88%), and MMMU (84.2%), and GPT-5 Pro reached 89.4% on GPQA Diamond and 42% on Humanity's Last Exam with extended reasoning and tools. It introduced the 400K context window standard and brought the Responses API tool surface (web search, file search, image generation, code interpreter, MCP) to flagship status. Unlike the GPT-5.4/5.5 generation, it predates native computer use, apply_patch, and skills.

Benchmarks

BenchmarkScoreSource
Humanity's Last Exam42%vellum.ai 2025-08-07T00:00:00.000Z
MMMU84.2%openai.com 2025-08-07T00:00:00.000Z
AIME 202594.6%openai.com 2025-08-07T00:00:00.000Z
GPQA Diamond89.4%vellum.ai 2025-08-07T00:00:00.000Z
Aider Polyglot88%openai.com 2025-08-07T00:00:00.000Z
SWE-bench Verified74.9%vellum.ai 2025-08-07T00:00:00.000Z

AI Panel Review

Six personas, six verdicts — the same panel that reviews every product on TopReviewed.

Decision Maker6/10
A capable legacy flagship — the only real question is when to migrate and to which target, not whether.

GPT-5 is a legacy flagship — still GA, still capable, but not the right choice for new builds. The strategic question for any team still on it is how soon to migrate and to which target: GPT-5.4 is the obvious quality-priority default (better capability, ~2x price), or GPT-5.4 mini for cost-priority workloads (better-than-GPT-5 coding at $0.75/$4.50). The chat-latest alias deprecation forces a 2026-10-23 deadline for teams using it; dated snapshots remain longer but won't see updates. The one durable reason to stay is fine-tuning, which the newer generation lacks. Plan the migration, don't drift.

Strategic Fit 6Vendor Risk 6Roadmap Confidence 6
Pros
  • capable
  • cheap
  • supports fine-tuning
Cons
  • stale knowledge
  • superseded
  • alias deprecation
Right for: in-flight builds and fine-tuning
Avoid if: starting a new build
Domain Strategist6.5/10
Its market is shrinking to fine-tuning and inertia — the newer generation owns the new-build narrative on both quality and cost.

Strategically, GPT-5's market has narrowed to two pockets: teams that fine-tune (the 5.4/5.5 generation does not offer it) and teams whose migration cost exceeds the upgrade value. On the open market it has no competitive wedge — GPT-5.4 beats it on quality at ~2x price and GPT-5.4 mini beats it on coding at lower cost. Its positioning is purely transitional. Market timing has fully passed; it is a 2025 model competing in a 2026 frontier. Differentiation survives only in the fine-tuning niche.

Competitive Positioning 6Differentiation 6Market Timing 5
Pros
  • fine-tuning niche
  • price
Cons
  • no new-build wedge
  • stale
Right for: fine-tuned deployments
Avoid if: you want frontier positioning
Finance Lead6/10
Genuinely cheap for the capability, but GPT-5.4 mini at $0.75/$4.50 with better coding is the comparison most migrations actually make.

$1.25/$10 is genuinely cheap for the capability level, which explains the stickiness. Cached input drops 90%, Batch halves both sides. For high-volume backend pipelines, GPT-5 may still pencil out below GPT-5.4 base. But GPT-5.4 mini at $0.75/$4.50 with comparable-or-better coding is the real comparison — most cost-aware migrations move from GPT-5 to mini, not to GPT-5.4 base. The cost case for staying is shrinking; migration is the right financial call within a quarter unless fine-tuning ties you here.

Cost Efficiency 7Pricing Transparency 8Value per Dollar 7
Pros
  • cheap
  • deep discounts
  • fine-tuning
Cons
  • mini is cheaper and codes better
Right for: cost-sensitive in-flight workloads
Avoid if: a clean migration to mini is available
Domain Practitioner7/10
Recognizably the modern API shape, minus the modern tools — no computer use, no apply_patch. For code agents, that gap is real.

Developers on GPT-5 recognize the entire current API shape — Responses, structured outputs, reasoning-effort dial. What's missing is the modern tool surface: no computer use, no apply_patch, no skills. For code-edit agents specifically, the move to the GPT-5.4 family is high-value because apply_patch is transformative for edits. SDK quality is identical to the current generation; promotion paths are clean. The chat-latest deprecation is the most concrete reason to migrate now — dated snapshots are safer but not future-proof. Fine-tuning support is the one thing developers would lose by moving.

API Ergonomics 8Tool/Agent Support 6Reliability 8
Pros
  • modern API shape
  • fine-tuning
  • clean promotion path
Cons
  • no apply_patch/computer use
  • alias deprecation
Right for: fine-tuning and non-agent workloads
Avoid if: you build code-edit agents
Power User7/10
ChatGPT users no longer meet GPT-5 directly — where it surfaces in unmigrated apps it's good, but the stale knowledge shows.

End users on ChatGPT no longer encounter GPT-5 directly — it has been replaced by 5.4 and 5.5 in default routing. Where it surfaces is in API-backed products that haven't migrated. Quality remains good for general chat; the 2024-09 knowledge cutoff occasionally surfaces in time-sensitive questions. Refusal patterns are slightly more conservative than the current generation. For most users the model is effectively invisible — they're getting GPT-5.4 or GPT-5.5 in ChatGPT and don't realize GPT-5 is still GA in the API.

Output Quality 7Speed 7Everyday Usefulness 7
Pros
  • good general chat
  • reasonable speed
Cons
  • stale knowledge
  • conservative refusals
Right for: unmigrated app backends
Avoid if: you need current-events accuracy
Skeptic6.5/10
The launch-day SOTA headlines are 20 months old — quoting GPT-5's 2025 benchmarks today is the polite way to say 'don't build here.'

The adversarial read: GPT-5's benchmark sheet is a 2025 time capsule. The AIME 94.6% and SWE-bench 74.9% were genuinely SOTA at launch, but GPT-5.4 nano — four tiers down and cheaper — now beats GPT-5 mini on coding, which tells you where the base sits. The model is still sold partly on launch-day prestige. The honest reasons to use it today are narrow and unglamorous: sunk-cost migration and fine-tuning. The alias deprecation (2026-10-23) is a forcing function the marketing soft-pedals. Nothing here is misleading — it's just an old model wearing its launch medals.

Claim Accuracy 7Weakness Severity 6Hype vs Reality 7
Pros
  • honest pricing
  • real fine-tuning value
Cons
  • dated benchmarks
  • deprecation pressure
Right for: skeptics with a fine-tuning lock-in
Avoid if: you'd be buying launch-day prestige

Strengths

  • Established benchmark leader at 2025-08 release; still strong for cost vs newer models.
  • $1.25/$10 pricing is a price/quality sweet spot for many production workloads.
  • 400K context handles most use cases.
  • Reasoning-effort dial covers chat and reasoning in one SKU.
  • Supports fine-tuning (the newer 5.4/5.5 generation does not).
  • Mature tool support via Responses API.

Limitations

  • Knowledge cutoff of 2024-09 is now ~20 months stale.
  • Superseded by GPT-5.4 on most benchmarks at comparable cost.
  • gpt-5-chat-latest alias is deprecated, shutdown 2026-10-23 — only dated snapshots stay stable.
  • No native computer use (added in GPT-5.4).
  • No apply_patch or skills (added in GPT-5.4).
  • Tool surface narrower than the current generation.

Best use cases

  • Existing production workloads validated on GPT-5 where migration cost outweighs the upgrade benefit.
  • Fine-tuning use cases that need a frontier-class base (5.4/5.5 do not offer fine-tuning).
  • Cost-sensitive interactive chat under 400K context not needing bleeding-edge capability.
  • Bridge SKU for organizations finishing migration to GPT-5.4/5.5.

Deep dive

The full research notes behind this review — verified against primary sources.

Architecture

OpenAI discloses no parameter counts, layer counts, or dense/MoE structure for GPT-5 — all null. It is a unified reasoning model with text + image input and text-only output, o200k_base tokenizer, and a 400K context window. The architectural milestone it introduced was conceptual rather than disclosed: collapsing chat and reasoning into one SKU with an effort dial, a pattern every subsequent GPT-5.x model inherited.

Capabilities

GPT-5 was the launch flagship and remains capable, justifying its 8.8 math and 8.5 reasoning scores — AIME 2025 94.6% (no tools) and GPQA Diamond 89.4% (Pro) were SOTA at release. Coding (8.0) is anchored by SWE-bench Verified 74.9% and Aider Polyglot 88% — strong for 2025 but now behind even GPT-5.4 nano on newer coding evals. Agentic (7.8) is capped by the absence of native computer use, apply_patch, and skills (all added in GPT-5.4). Long-context (8.0) reflects the 400K window. Multilingual (8.5), instruction-following (8.7), and function-calling (8.5) are solid. Vision (8.2) and document/OCR (8.0) handle image input. Real-time data (5.5) is the weak axis: a 2024-09 cutoff is now ~20 months stale, so time-sensitive answers lean heavily on the web-search tool.

Benchmark analysis

Benchmark Score vs Successor (GPT-5.4) vs Top Competitor (at release) Source
AIME 2025 (no tools) 94.6% superseded leader at release OpenAI
GPQA Diamond (Pro) 89.4% below GPT-5.4 (92.8%) leader at release Vellum
SWE-bench Verified 74.9% below newer gen leader at release Vellum
Aider Polyglot 88% superseded leader at release OpenAI
MMMU 84.2% below GPT-5.4 MMMU-Pro context leader at release OpenAI
HLE (Pro, with tools) 42% peer with newer no-tools figures leader at release Vellum

AIME/GPQA/HLE figures reflect GPT-5 Pro extended reasoning where noted; SWE-bench and Aider are GPT-5 with thinking. MMLU-Pro, MATH-500, HumanEval, LiveCodeBench, IFEval, BBH, Tau-bench, SimpleQA, and LMArena have no clean GPT-5-base figure recorded here and are null.

Speed & latency

GPT-5 serves at roughly 90 tokens/sec at high reasoning on OpenAI's API, with time-to-first-token around 1 second at low/default effort. latency_tier is medium — interactive for chat, slower at high reasoning effort. It is generally faster to first token than the heavier GPT-5.5 because the model is smaller and older, but it lacks the serving-infrastructure improvements that shipped with GPT-5.5.

Pricing analysis

Surface Cost Notes
API input $1.25 / 1M tok
API output $10.00 / 1M tok
Cached input $0.125 / 1M tok 90% discount
Batch (in/out) $0.625 / $5.00 50% off, 24h SLA
Direct UI $20/mo (Plus) superseded in default routing
Free tier none
Fine-tuning available GPT-5 supports fine-tuning (newer 5.4/5.5 do not)
Deprecation gpt-5-chat-latest shutdown 2026-10-23 dated snapshots remain
Rate limits ~10,000 RPM / ~30M TPM tier-dependent

Reasoning-token note: hidden reasoning tokens bill as output tokens at higher effort tiers.

Deployment & access

API-only via the Responses API; not open-weights, license Proprietary, not self-hostable. Cloud-managed via Azure OpenAI and Azure AI Foundry; OpenRouter proxies it. Data residency covers US and EU. Notably, GPT-5 supports fine-tuning where the newer GPT-5.4/5.5 generation does not — a real reason some teams remain on it. The tool surface predates computer use, apply_patch, and skills.

Safety & privacy

Governed by OpenAI's Preparedness Framework. No training on API inputs by default; opt-out and zero-retention available for enterprise. Compliance covers SOC2, GDPR, CCPA, and HIPAA (BAA). Content moderation is built in. Refusal behavior is slightly more conservative than the current GPT-5.4/5.5 generation.

Ecosystem & tooling

First-party SDKs in Python, TypeScript, Java, Go, and .NET, plus the OpenAI Agents SDK. Framework integrations span LangChain, LlamaIndex, Vercel AI SDK, and Pydantic AI. It was the ChatGPT default through late 2025 and powered Microsoft Copilot during that window. Popularity tier: growing (declining as migration proceeds), still widely embedded in API-backed products.

Buyer questions

Should I start a new build on GPT-5?

No — use GPT-5.4 (quality) or GPT-5.4 mini (cost). GPT-5 is a legacy flagship for in-flight workloads.

Is GPT-5 being retired?

The base model is not on the deprecation list, but the gpt-5-chat-latest alias shuts down 2026-10-23. Pin a dated snapshot if you stay.

Why would I keep using it?

Two reasons: a validated in-flight workload where migration cost exceeds the benefit, or fine-tuning (which GPT-5.4/5.5 do not offer).

How stale is the knowledge?

The cutoff is 2024-09 — about 20 months. Time-sensitive queries need the web-search tool.

What does migration cost?

Mostly prompt re-validation; the API shape is identical across the family, so promotion is a model-name change plus testing.

Is my data used for training?

No, not by API default; enterprise opt-out and zero-retention exist.

Comparable models

GPT-5.4 miniOpenAI

recommended cost-priority successor; cheaper at $0.75/$4.50 with better coding.

GPT-5.4 baseOpenAI

recommended quality-priority successor; better capability at ~2x the price plus computer use and apply_patch.

Claude Sonnet 4.5Anthropic

generational peer from the 2025 cohort; comparable role and pricing.

Gemini 2.5 ProGoogle

generational peer; comparable pricing and capability for the era.

Sources

Primary references used to verify this review.

Model specs

Input price
$1.25 / Mtok
Output price
$10 / Mtok
Cached input
$0.13 / Mtok
Batch (in/out)
$0.63 / $5
Context window
400K tokens
Max output
128K tokens
Knowledge cutoff
2024-09
Released
2025-08-06
Modalities
text, image → text
Output speed
~90 tok/s
License
Proprietary
Clouds
Azure OpenAI, Azure AI Foundry

Does not train on API inputs by default

Last verified 2026-05-27