Inference
EN
OpenAI

GPT-5 (high)

GPT-5 (high) is a reasoning model from OpenAI in the GPT-5 family. 13 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Reasoning
  • Input: text · image · file
  • Released 2025-08
  • Retires 11 Dec 2026
RankedEnough results for an index.
IndexAll categories, out of 100.53.6±5.0Median 51.0
CoverageIndex weight that has results.95%
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.$1.25Median $0.60
Output / 1MUS dollars per 1M output tokens.$10.00Median $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 counted49.7130 / 218
CodingCode writing and repair.1 counted59.5—
ReasoningLogic problems and puzzles.2 counted54.488 / 227
MultimodalTasks with images and text.1 counted51.7—
KnowledgeFacts and expert knowledge.4 counted56.185 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted57.3—
MathMath problems.1 counted49.2—

Results

13 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Artificial Analysis MATH-500Math99.4%1 / 9
Artificial Analysis IFBenchInstruction73.1%32 / 146
Artificial Analysis Omniscience AccuracyKnowledge40.3%50 / 164
Artificial Analysis Long Context ReasoningReasoning78.2%68 / 217
Critical Physics TasksReasoning5.7%78 / 214
Artificial Analysis GPQA DiamondKnowledge85.4%76 / 199
τ²-Bench Tool-Agent-User EvaluationAgentic84.8%58 / 149
Artificial Analysis Humanity's Last ExamKnowledge28.5%87 / 222
Artificial Analysis MMLU-ProKnowledge87.1%6 / 15
Artificial Analysis MMMU-ProMultimodal74.2%60 / 113
Artificial Analysis LiveCodeBenchCoding84.6%7 / 12
GDPval-AA normalizedAgentic20.9%81 / 133
JobBenchAgentic8.5%36 / 36
Artificial Analysis AIME 2025Math94.3%—
Artificial Analysis Global-MMLU-LiteMultilingual90.7%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuse

History

5 releases
Index53.8 → 53.6
23 Oct 202612 Nov 2026
Output / 1M$10.00 → $10.00
23 Oct 202612 Nov 2026

Questions

How much does GPT-5 (high) cost?
$1.25 per 1M input tokens, $10.00 per 1M output tokens.
How good is GPT-5 (high)?
Its index is 53.6 out of 100. That is place 112 of 283 ranked models.
What is GPT-5 (high) best at?
Knowledge: 56.1 out of 100, place 85 of 268.
How fast is GPT-5 (high)?
76 output tokens per second, 4.6 s to the first token.
What is the context window of GPT-5 (high)?
400K tokens.
Is GPT-5 (high) open source?
No. Its weights are not published.
When was GPT-5 (high) released?
August 2025.

Badge

GPT-5 (high) on Inference360: place 112 of 283, index 53.6
HTML
<a href="https://inference360.ai/models/gpt-5-high"><img src="https://inference360.ai/badges/gpt-5-high.svg" alt="GPT-5 (high) on Inference360: place 112 of 283, index 53.6" height="20"></a>
Markdown
[![GPT-5 (high) on Inference360: place 112 of 283, index 53.6](https://inference360.ai/badges/gpt-5-high.svg)](https://inference360.ai/models/gpt-5-high)

Compare with

GPT-5.1-Codex-Max53.8GPT-5 (medium)53.0GPT-OSS 20B41.7

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from OpenAI

All models
GPT-5 (medium)53.0GPT-5 mini48.4GPT-5 nano41.9GPT-555.0GPT-OSS 120B43.4