llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGPT-5

OpenAI model product

GPT-5

GPT-5 Medium balances reasoning depth with response speed, providing medium-effort thinking for moderately complex tasks. Optimized for coding and agentic tasks, this variant offers more thorough analysis than instant responses while maintaining faster performance than high-effort reasoning.

Updated Aug 10, 2026. Default version: GPT-5 Medium

Compare
LLMBoard score71.6GPT-5
Coverage100%13 benchmark families
Context window400KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
GPT-5 Medium
Released
Aug 7, 2025
Knowledge cutoff
Sep 30, 2024
Parameters
N/A
Context window
400K
Max output
128K
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

GPT-5 category scores

Benchmark results

Published benchmark records for the scored version GPT-5.

34 rows
Columns

Show columns

Aider-Polyglot0.9122100.0%CAug 7, 2026
COLLIE1.0110100.0%CAug 7, 2026
Internal API instruction following (hard)0.617100.0%CAug 7, 2026
LongFact Concepts0.011100.0%CAug 7, 2026
LongFact Objects0.011100.0%CAug 7, 2026
MMLU0.91100100.0%CAug 7, 2026
OpenAI-MRCR: 2 needle 128k1.019100.0%CAug 7, 2026
OpenAI-MRCR: 2 needle 256k0.911100.0%CAug 7, 2026
SWE-Lancer (IC-Diamond subset)1.016100.0%CAug 7, 2026
BrowseComp Long Context 128k0.92575.0%CAug 7, 2026
BrowseComp Long Context 256k0.9220.0%CAug 7, 2026
FActScore0.0220.0%CAug 7, 2026
HumanEval0.947696.0%CAug 7, 2026
Multi-Challenge0.742989.3%CAug 7, 2026
ERQA0.752381.8%CAug 7, 2026
Graphwalks parents <128k0.751876.5%CAug 7, 2026
MMMU0.856393.5%CAug 7, 2026
VideoMME w sub.0.951055.6%CAug 7, 2026
Graphwalks BFS <128k0.862276.2%CAug 7, 2026
Tau2 Retail0.872676.0%CAug 7, 2026
VideoMMMU0.872676.0%CAug 7, 2026
HealthBench Hard0.0990.0%CAug 7, 2026
Tau2 Telecom1.093576.5%CAug 7, 2026
FrontierMath0.3111737.5%CAug 7, 2026
Tau2 Airline0.6112354.5%CAug 7, 2026
HMMT 20250.9123365.6%CAug 7, 2026
MATH0.8137182.9%CAug 7, 2026
CharXiv-R0.8184763.0%CAug 7, 2026
MMMU-Pro0.8196571.9%CAug 7, 2026
AIME 20250.92211481.4%CAug 7, 2026
SWE-Bench Verified0.73410468.0%CAug 7, 2026
BrowseComp0.5395833.3%CAug 7, 2026
GPQA0.94923379.3%CAug 7, 2026
Humanity's Last Exam0.2509246.1%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

3 rows
Columns

Show columns

webdevwebdev-html521428.73,021N/AAug 6, 2026
webdevoverall551418.63,021N/AAug 6, 2026
webdevwebdev551418.63,021N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No published price snapshot

The default version has no provider offering with current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GPT-5 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

3 rows
Columns

Show columns

GPT-5Aug 7, 202571.6N/A400K128KNoProprietary
GPT-5 HighAug 7, 2025N/AN/A400K128KNoProprietary
GPT-5 MediumAug 7, 2025N/AN/A400K128KNoProprietary

What is GPT-5?

A concise description based on the published model registry.

GPT-5 Medium balances reasoning depth with response speed, providing medium-effort thinking for moderately complex tasks. Optimized for coding and agentic tasks, this variant offers more thorough analysis than instant responses while maintaining faster performance than high-effort reasoning.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

GPT-5 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GPT-5vsNemotron 3 UltraGPT-5vsDeepSeek-V4-FlashGPT-5vsKimi K2.5GPT-5vsLlama 3.1 405BGPT-5vsDeepSeek-V2.5GPT-5vsClaude Opus 4.6

Models similar to GPT-5

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#34-2.5
OP

GPT-5.2

OpenAI

69.1 LLMBoard

DetailsCompare
#17+4.0
OP

GPT-5.4

OpenAI

75.6 LLMBoard

DetailsCompare
#16+5.2
OP

GPT-5.5

OpenAI

76.8 LLMBoard

DetailsCompare
#15+5.6
OP

GPT-5.6-Luna

OpenAI

77.2 LLMBoard

DetailsCompare
#45-8.6
OP

o1

OpenAI

63.0 LLMBoard

DetailsCompare
#49-10.0
OP

o3 mini

OpenAI

61.6 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-5.

When was GPT-5 released?

GPT-5's default version was released on Aug 7, 2025.

How much does GPT-5 cost?

No official standard PAYG price is currently available for GPT-5.

Who created GPT-5?

GPT-5 is published under OpenAI in the model registry.

What is the context window for GPT-5?

The default version has a 400K token context window.

Is GPT-5 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer GPT-5?

No published provider offering is currently linked to the default version.

What models should I compare GPT-5 with?

Nearby ranked alternatives include Nemotron 3 Ultra, DeepSeek-V4-Flash, Kimi K2.5.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai