VerdictPal
Join

Models / OpenAI

OpenAI o3

OpenAI o · Released 2025-04-16

OpenAI's April 2025 reasoning model. Extended thinking for math, code, and science. LiveBench 68.5%, LongBench v2 51.2%, BFCL 78.1%.

Reasoning-tier OpenAI pick when latency and cost are secondary to hardest single-shot problem solving.

#34 of 51 on AA Index · current snapshot
30 AA Index · 21 benchmark rows · 7 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite70
Context200K
Input / 1M—
Output / 1M—
Knowledge cutoff2024-06-01
Output speed155 t/s
TTFT (default API)4.84s
Statussolid
ChatGPT
KnowledgeReasoningMathCodingAgenticLong contextTool use
Knowledge
85
Reasoning
88
Math
99
Coding
95
Agentic
81
Long context
69
Tool use
78

85average across 7 tested families

Benchmark placements

Where OpenAI o3 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#1/ 2099Artificial Analysis2026-07-21
LiveCodeBenchCoding#4/ 1381Artificial Analysis2026-07-21
MMLU-ProKnowledge#6/ 2185Artificial Analysis2026-07-21
AIMEMath#8/ 1988Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#11/ 6481Artificial Analysis2026-07-21
AA output speedPerformance#16/ 69Artificial Analysis2026-07-21
AA time to first tokenPerformance#26/ 69Artificial Analysis2026-07-21
AA-LCRLong context#27/ 6469Artificial Analysis2026-07-21
IFBenchReasoning#30/ 5771Artificial Analysis2026-07-21
GPQA DiamondReasoning#43/ 6983Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#45/ 6520Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#48/ 6730Artificial Analysis2026-07-21
SciCodeCoding#49/ 6541Artificial Analysis2026-07-21
Terminal-BenchAgentic#55/ 6937Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where OpenAI o3 shows up, it's highlighted.

KnowledgeOpenAI o3 · 85
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningOpenAI o3 · 88
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
MathOpenAI o3 · 99
  1. 1
    OpenAI o3
    99
  2. 2
    OpenAI o1
    97
  3. 3
    Gemini 3 Pro
    96
CodingOpenAI o3 · 95
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticOpenAI o3 · 81
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextOpenAI o3 · 69
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Tool useOpenAI o3 · 78
  1. 1
    Claude Sonnet 4.6
    89
  2. 2
    GPT 5.5
    87
  3. 3
    Claude Opus 4.8
    87
Newest receipts

Benchmark rows added to the public ledger for OpenAI o3 in the last 120 days. Older rows live in the full table below.

17 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context69.33%Artificial Analysis2
AA output speedPerformance155 t/sArtificial Analysis2
AA time to first tokenPerformance4.84sArtificial Analysis2
AIMEMath88.33%Artificial Analysis2
Artificial Analysis Intelligence IndexReasoning30.4%Artificial Analysis2
GPQA DiamondReasoning82.7%Artificial Analysis2
Humanity's Last ExamReasoning20%Artificial Analysis2
IFBenchReasoning71.43%Artificial Analysis2
LiveCodeBenchCoding80.8%Artificial Analysis2
MATHMath99.2%Artificial Analysis2
MMLU-ProKnowledge85.3%Artificial Analysis2
SciCodeCoding41%Artificial Analysis2
τ³-Bench BankingAgentic80.7%Artificial Analysis2
Terminal-BenchAgentic37.12%Artificial Analysis2
BFCLTool use78.1%Berkeley Function Calling Leaderboard V499
LiveBenchReasoning68.5%LiveBench leaderboard99
LongBench v2Long context51.2%LongBench v2 leaderboard113
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.

Knowledge85
Reasoning88
Math99
Coding95
Agentic81
Long context69
Tool use78
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 o3. Scores link to the original source; gaps mean no public row exists yet.

21 sourced rows

19 of 32 catalog benchmarks have a sourced row for OpenAI o3.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Tool use

Performance

Sources