GPT-5 (ChatGPT)
OpenAIGPT
Release Date
2025-08-07
Parameters
—
Context Length
400K
Modalities
image, text
Capability Radar
34
general
51
coding
52
reasoning
45
scienceest.
80
agents
90
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 62 | 55.0 | LS |
| Code Ranking | 161 | 54.0 | AA |
| General Ranking | 290 | 37.0 | AA |
| Math Reasoning | 186 | 49.0 | AA |
| Multimodal Ranking | 25 | 84.0 | LS |
| Reasoning | 45 | 72.0 | LS |
| Science | 217 | 47.0 | AA |
Benchmark Scores (LLM Stats)
Agents
BrowseComp
54.9%SR
Biology
GPQA
85.7%SR
Code
SWE-Lancer (IC-Diamond subset)
100.0%SR
HumanEval
93.4%SR
Aider-Polyglot
88.0%SR
SWE-Bench Verified
74.9%SR
Communication
Tau2 Telecom
96.7%SR
Tau2 Retail
81.1%SR
Multi-Challenge
69.6%SR
Tau2 Airline
62.6%SR
Finance
MMLU
92.5%SR
General
MMMU
84.2%SR
MMMU-Pro
78.4%SR
Internal API instruction following (hard)
64.0%SR
LongFact Objects
0.8%SR
LongFact Concepts
0.7%SR
Healthcare
VideoMMMU
84.6%SR
HealthBench Hard
1.6%SR
Language
COLLIE
99.0%SR
Long Context
OpenAI-MRCR: 2 needle 128k
95.2%SR
OpenAI-MRCR: 2 needle 256k
86.8%SR
Math
AIME 2025
94.6%SR
HMMT 2025
93.3%SR
MATH
84.7%SR
FrontierMath
26.3%SR
Humanity's Last Exam
24.8%SR
Multimodal
VideoMME w sub.
86.7%SR
CharXiv-R
81.1%SR
Reasoning
BrowseComp Long Context 128k
90.0%SR
BrowseComp Long Context 256k
88.8%SR
Graphwalks BFS <128k
78.3%SR
Graphwalks parents <128k
73.3%SR
ERQA
65.7%SR
FActScore
1.0%SR
AA Evaluation Indices
Math Index48.3
Intelligence Index15.3
Mmlu Pro0.8
Gpqa0.7
Lcr0.6
Livecodebench0.5
Aime 250.5
Ifbench0.5
Scicode0.4
Terminalbench Hard0.1
Hle0.1
Tau20.0
LLM Stats Category Scores
Language100
Long Context100
Writing100
Legal90
Physics90
Finance90
Biology90
Chemistry90
Code90
Video90
Reasoning80
General80
Communication80
Tool Calling80
Math70
Multimodal70
Search70
Frontend Development70
Healthcare70
Vision70
Spatial Reasoning60
Structured Output60
Agents50
Robotics20
Pricing
Input Price$1.25 / 1M tokens
Output Price$10 / 1M tokens
Blended Price (3:1)$3.438 / 1M tokens
Cache Read Price$0.125 / 1M tokens
Speed
Tokens/sec193.1
Time to First Token0.49s
Time to Answer0.49s
Provider Price Ranking
Provider Price Ranking
10 providers
Cheapest: OpenCode ZenMost Expensive: Neon
ProviderInputOutput
1OpenCode ZenCheapest
$1.07
$8.5
2OpenAIPRIMARY
$1.25
$10
3302.AI
$1.25
$10
4Abacus
$1.25
$10
5SAP AI Core
$1.25
$10
6Helicone
$1.25
$10
7Azure Cognitive Services
$1.25
$10
8LLM Gateway
$1.25
$10
9Azure
$1.25
$10
10Neon
$1.25
$10
Compare pricing across different API providers for this model.