VerdictPal
Join

Models / OpenAI

OpenAI o1

OpenAI o · Released 2024-09-12

OpenAI's September 2024 reasoning model. AIME 2024 83.3% with cons@64 sampling. Predecessor to o3 and GPT-5 reasoning tiers.

Legacy reasoning tier — prefer o3 or GPT-5.5 for new math and code work.

#37 of 51 on AA Index · current snapshot
23 AA Index · 14 benchmark rows · 2 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite55
Context200K
Input / 1M—
Output / 1M—
Knowledge cutoff2023-10-01
Output speed0 t/s
TTFT (default API)0.00s
Statuslightweight
ChatGPT
KnowledgeReasoningMathCodingAgenticLong context
Knowledge
84
Reasoning
75
Math
97
Coding
68
Agentic
63
Long context
59

74average across 6 tested families

Benchmark placements

Where OpenAI o1 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#2/ 2097Artificial Analysis2026-07-21
LiveCodeBenchCoding#8/ 1368Artificial Analysis2026-07-21
MMLU-ProKnowledge#8/ 2184Artificial Analysis2026-07-21
AIMEMath#12/ 1983OpenAI: Learning to Reason2024-09-12
τ³-Bench BankingAgentic#14/ 6463Artificial Analysis2026-07-21
IFBenchReasoning#34/ 5770Artificial Analysis2026-07-21
AA-LCRLong context#46/ 6459Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#53/ 6723Artificial Analysis2026-07-21
SciCodeCoding#56/ 6536Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#57/ 658Artificial Analysis2026-07-21
GPQA DiamondReasoning#58/ 6975Artificial Analysis2026-07-21
Terminal-BenchAgentic#63/ 6913Artificial Analysis2026-07-21
AA output speedPerformance#69/ 69Artificial Analysis2026-07-21
AA time to first tokenPerformance#69/ 69Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where OpenAI o1 shows up, it's highlighted.

KnowledgeOpenAI o1 · 84
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningOpenAI o1 · 75
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
MathOpenAI o1 · 97
  1. 1
    OpenAI o3
    99
  2. 2
    OpenAI o1
    97
  3. 3
    Gemini 3 Pro
    96
CodingOpenAI o1 · 68
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticOpenAI o1 · 63
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextOpenAI o1 · 59
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

Benchmark rows added to the public ledger for OpenAI o1 in the last 120 days. Older rows live in the full table below.

13 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context59.33%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning23.4%Artificial Analysis2
GPQA DiamondReasoning74.7%Artificial Analysis2
Humanity's Last ExamReasoning7.7%Artificial Analysis2
IFBenchReasoning70.34%Artificial Analysis2
LiveCodeBenchCoding67.9%Artificial Analysis2
MATHMath97%Artificial Analysis2
MMLU-ProKnowledge84.1%Artificial Analysis2
SciCodeCoding35.8%Artificial Analysis2
τ³-Bench BankingAgentic62.57%Artificial Analysis2
Terminal-BenchAgentic12.88%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.

Knowledge84
Reasoning75
Math97
Coding68
Agentic63
Long context59
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for OpenAI o1. Scores link to the original source; gaps mean no public row exists yet.

14 sourced rows

14 of 32 catalog benchmarks have a sourced row for OpenAI o1.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources