VerdictPal
Join

Models / OpenAI

GPT-5 (low)

GPT-5 (low) · Released 2025-08-07

AA Intelligence Index 31.9. Listed on Artificial Analysis with API pricing $1.25/$10 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#116 of 166 on AA Index · current snapshot
32 AA Index · 13 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite60
ContextUnlisted
Input / 1M$1.3
Output / 1M$10
Knowledge cutoffunpublished
Statuslightweight

Family profile

Best published score in each covered benchmark family.

72/100 avg
Knowledge
86
Reasoning
81
Math
99
Coding
76
Agentic
27
Long context
64

6 tested benchmark families

Benchmark placements

Where GPT-5 (low) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
MATHMath#5/ 2599Artificial Analysis2026-09-01
MMLU-ProKnowledge#18/ 3986Artificial Analysis2026-09-01
LiveCodeBenchCoding#20/ 3176Artificial Analysis2026-09-01
AIMEMath#27/ 3783Artificial Analysis2026-09-01
IFBenchReasoning#66/ 12767Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#123/ 18020Artificial Analysis2026-09-01
AA output speedPerformance#125/ 185Artificial Analysis2026-09-01
AA time to first tokenPerformance#125/ 185Artificial Analysis2026-09-01
AA-LCRLong context#127/ 17964Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#135/ 18432Artificial Analysis2026-09-01
SciCodeCoding#135/ 18039Artificial Analysis2026-09-01
GPQA DiamondReasoning#137/ 18581Artificial Analysis2026-09-01
Terminal-BenchAgentic#160/ 18427Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where GPT-5 (low) shows up, it's highlighted.

KnowledgeGPT-5 (low) · 86
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningGPT-5 (low) · 81
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
MathGPT-5 (low) · 99
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    GPT-5 (high)
    99
CodingGPT-5 (low) · 76
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5 (low) · 27
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5 (low) · 64
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for GPT-5 (low) in the last 120 days. Older rows live in the full table below.

13 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context63.67%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
AIMEMath83%Artificial Analysis2
Artificial Analysis Intelligence IndexReasoning31.9%Artificial Analysis2
GPQA DiamondReasoning80.8%Artificial Analysis2
Humanity's Last ExamReasoning19.6%Artificial Analysis2
IFBenchReasoning66.6%Artificial Analysis2
LiveCodeBenchCoding76.3%Artificial Analysis2
MATHMath98.73%Artificial Analysis2
MMLU-ProKnowledge86%Artificial Analysis2
SciCodeCoding39.1%Artificial Analysis2
Terminal-BenchAgentic26.52%Artificial Analysis2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Knowledge86
Reasoning81
Math99
Coding76
Agentic27
Long context64
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GPT-5 (low). Scores link to the original source; gaps mean no public row exists yet.

13 sourced rows

13 of 37 catalog benchmarks have a sourced row for GPT-5 (low).

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources