GPT-5 (medium)

GPT-5 (medium) is a reasoning model from OpenAI in the GPT-5 family. 9 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.54.7 ±8.9
CoverageShare of the index weight with results.65%
SpeedOutput tokens per second.62/s
Input / 1MUS dollars per 1M input tokens.$1.25
Output / 1MUS dollars per 1M output tokens.$10
ContextMaximum tokens in one request.400K
EloLMArena rating and rank.1406 (#136)

The index is a score out of 100. The ± range shows how much it can change.

31,428 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
60.9
CodingCode writing and repair.
N/A
ReasoningLogic problems and puzzles.
49.6
MultimodalTasks with images and text.
57.9
KnowledgeFacts and expert knowledge.
55.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
60.7
MathMath problems.
N/A

Results

9 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Artificial Analysis MATH-500Math99.1%Artificial Analysis
τ²-Bench Tool-Agent-User EvaluationAgentic86.5%60.9Victor Barres et al.
Artificial Analysis GPQA DiamondKnowledge84.2%54.8Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning76.0%60.8Artificial Analysis
Artificial Analysis MMMU-ProMultimodal74.3%57.9Artificial Analysis
Artificial Analysis IFBenchInstruction70.6%60.7Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge39.5%62.7Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge25.4%52.1Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge22.9%51.0Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial Analysis

9 benchmarks count, from 9 of 10 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence stated

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from OpenAI

GPT-6 Astra83.5GPT-5.6 Sol76.7GPT-5.6 Terra73.4GPT-6 Sol76.9GPT-5.572.3