Inference
EN
OpenAI

GPT-5

GPT-5 is a model from OpenAI. 25 benchmarks count toward its index, in 6 categories.

  • Input: text · image · file
  • Released 2025-08
  • Retires 11 Dec 2026
RankedEnough results for an index.
IndexAll categories, out of 100.55.0±4.2Median 51.0
CoverageIndex weight that has results.90%
SpeedOutput tokens per second.76/sMedian 67/s
First tokenSeconds to the first output token.4.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.25batch $0.625Median $0.60
Output / 1MUS dollars per 1M output tokens.$10.00batch $5.00 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.400KMedian 262K
EloLMArena rating and rank.1406±4 #149Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-5
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
30 Sep 2024
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.125
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
11 Dec 2026

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.3 counted53.1113 / 218
CodingCode writing and repair.5 counted52.5123 / 209
ReasoningLogic problems and puzzles.5 counted55.484 / 227
MultimodalTasks with images and text.1 counted61.2—
KnowledgeFacts and expert knowledge.3 counted58.475 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.8 counted55.363 / 168

Results

25 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH level 5Math98.1% ±0.31 / 88
MATH 500Math96.0% ±0.93 / 59
AIMEMath93.4% ±1.314 / 95
SWE-bench Verified · swebench.comCoding65.0%7 / 46
LiveCodeBenchCoding85.9% ±1.025 / 142
FrontierMath-2025-02-28-PrivateMath32.4% ±2.816 / 69
τ²-bench RetailAgentic81.6%6 / 23
Terminal-Bench 1.0Agentic48.8% ±5.613 / 47
τ²-bench TelecomAgentic95.8%5 / 18
OTIS Mock AIME 2024-2025Math91.4% ±3.756 / 200
MMLU ProKnowledge86.5% ±0.341 / 135
FrontierMath-Tier-4-2025-07-01-PrivateMath12.5% ±4.817 / 55
GPQA diamond · Epoch AIKnowledge86.2% ±2.168 / 217
SimpleQA VerifiedKnowledge50.1% ±1.630 / 91
GPQA Diamond · Vals AIKnowledge85.6% ±1.845 / 135
SWE-bench Verified · SWE-bench/experimentsCoding65.0%22 / 65
IOI v1Coding20.0% ±4.624 / 61
MMMU ProMultimodal81.5% ±0.939 / 92
Chess PuzzlesReasoning36.0% ±4.842 / 90
Mystery Game PuzzlesReasoning23.0% ±4.239 / 80
ARC-AGI-1 (semi-private)Reasoning65.7%62 / 126
ARC-AGI-2 (semi-private)Reasoning9.9%68 / 131
τ²-bench AirlineAgentic62.5%12 / 22
FrontierMath-Tiers-1-3-v2-PrivateMath55.4% ±2.951 / 90
Terminal-Bench 2.0 · Vals AIAgentic37.1% ±5.138 / 66
SWE-Bench verified · Epoch AICoding73.6% ±2.019 / 32
FrontierMath-Tier-4-v2-PrivateMath22.0% ±6.548 / 72
Vibe Code Bench v1.1Coding20.1% ±3.491 / 123
SWE-benchCoding69.0% ±2.167 / 87
EBR-benchReasoning12.7%24 / 31
MirrorCodeCoding4.4% ±3.439 / 39
MedQAHealthcare96.3% ±0.24 / 95
FrontierMath-Tier-4-2025-07-01-PublicMath0.0%3 / 36
CaseLaw v2Legal66.5% ±0.76 / 53
LegalBenchLegal86.0% ±0.417 / 149
FrontierMath-2025-02-28-PublicMath60.0% ±16.311 / 64
MGSMMultilingual92.8% ±1.614 / 74
MedCodeHealthcare49.6% ±2.121 / 106
TaxEval v2Finance73.4% ±0.949 / 143
MedScribeHealthcare83.7% ±1.942 / 109
MortgageTaxFinance65.5% ±0.941 / 97
CorpFin v2Finance61.1% ±1.058 / 131
ARC-AGI-2 (public eval)Reasoning9.6%59 / 122
Finance Agent v1.1Finance52.2% ±2.925 / 51
ARC-AGI-1 (public eval)Reasoning65.9%62 / 116

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYVals AINo licence statedSierra ResearchMITARC Prize FoundationTerms restrict reuseSWE-bench teamNo licence stated

History

5 releases
Index56.3 → 55.0
23 Oct 202612 Nov 2026
Output / 1M$10.00 → $10.00
23 Oct 202612 Nov 2026

Questions

How much does GPT-5 cost?
$1.25 per 1M input tokens, $10.00 per 1M output tokens.
How good is GPT-5?
Its index is 55.0 out of 100. That is place 103 of 283 ranked models.
What is GPT-5 best at?
Knowledge: 58.4 out of 100, place 75 of 268.
How fast is GPT-5?
76 output tokens per second, 4.6 s to the first token.
What is the context window of GPT-5?
400K tokens.
When was GPT-5 released?
August 2025.

Badge

GPT-5 on Inference360: place 103 of 283, index 55.0
HTML
<a href="https://inference360.ai/models/openai-gpt-5"><img src="https://inference360.ai/badges/openai-gpt-5.svg" alt="GPT-5 on Inference360: place 103 of 283, index 55.0" height="20"></a>
Markdown
[![GPT-5 on Inference360: place 103 of 283, index 55.0](https://inference360.ai/badges/openai-gpt-5.svg)](https://inference360.ai/models/openai-gpt-5)

Compare with

Gemini 3 Flash55.0Inkling-Small55.1GPT-5.155.3MiMo-V2.554.8GPT-5 nano41.9

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeGLM-5.3-Flash63.1 · $0.078/1M

More from OpenAI

All models
GPT-5 (high)53.6GPT-5 (medium)53.0GPT-5 mini48.4GPT-5 nano41.9GPT-OSS 120B43.4