priorsBuilder

OpenAI · released 2026-03-17

GPT-5.4 Nano

Measured on 67 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #162xhigh of 58728.3%
  2. #238medium of 58715.9%
  3. #524none of 5874.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #231medium of 526-18.0
  2. #269xhigh of 526-29.5
  3. #301none of 526-37.5

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #160high of 19614.0%
  2. #161none of 19614.0%
  3. #171xhigh of 19610.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #58high of 7012.2%

Leader: GPT-6.1 Sol · 100.0%

All 67 benchmarks

show 63 more

agentic

AA-Briefcase v1.1

224 results
  1. #164xhigh of 224674

Leader: Sonnet 5.5 · 1823

agentic

APEX-Agents-AA

33 results
  1. #18xhigh of 3324.9%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench-AA

219 results
  1. #156xhigh of 2196.0%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #40xhigh of 5031.5%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #68high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

ITBench-AA

45 results
  1. #37xhigh of 4524.4%
  2. #42none of 4512.9%

Leader: GPT-5.6 Sol · 56.2%

agentic

Legal Research Bench

78 results
  1. #72high of 786.3%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #65high of 695.0%

Leader: Fable 5.1 · 49.2%

agentic

τ²-Bench Telecom

393 results
  1. #137xhigh of 39376.0%
  2. #196medium of 39352.6%
  3. #238none of 39334.8%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #76xhigh of 20627.4%

Leader: Qwen 3.8 Max · 51.3%

coding

Code Migration

77 results
  1. #55high of 7714.5%

Leader: Sonnet 5.5 · 69.8%

coding

LiveCodeBench (Vals)

127 results
  1. #42high of 12784.0%

Leader: Fable 5.1 · 90.5%

coding

SciCode

226 results
  1. #127xhigh of 22647.2%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #61high of 8569.8%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #33high of 6339.9%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #67high of 7441.6%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #49xhigh of 38742.4%
  2. #93medium of 38733.3%
  3. #147none of 38724.2%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #99xhigh of 23860.7%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #141xhigh of 2160.5%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #66high of 10526.1%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #64xhigh of 12749.2%
  2. #96none of 12738.0%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #217xhigh of 61020.7
  2. #229medium of 61020.0
  3. #338none of 61011.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #122high of 2201401

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #113high of 2201413

Leader: Gemini 4 · 1553

composite

Vals Multimodal Index v1.2

33 results
  1. #28high of 3347.6%

Leader: Fable 5 · 74.2%

cost

AA Intelligence Index Cost per Task

177 results
  1. #54xhigh of 177$0.18

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #55xhigh of 177$331

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #48xhigh of 721296

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #57high of 11761.2%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #57high of 7444.8%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #63high of 7838.2%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #142xhigh of 2107.8%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #169xhigh of 288948

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #64high of 8459.1%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #96high of 12567.4%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #25xhigh of 39975.9%
  2. #108medium of 39964.4%
  3. #324none of 39932.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #217xhigh of 52625.7%
  2. #269medium of 52621.9%
  3. #405none of 52614.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #117medium of 52648.9%
  2. #164none of 52638.5%
  3. #231xhigh of 52625.8%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

CaseLaw (Vals)

53 results
  1. #46high of 5351.9%

Leader: Grok 4.3 · 79.3%

knowledge

GPQA Diamond

539 results
  1. #176xhigh of 53981.7%
  2. #235medium of 53976.1%
  3. #388none of 53955.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #75high of 12277.5%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #55high of 9441.0%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #63high of 9677.1%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #98high of 12277.2%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #56high of 8173.6%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #169xhigh of 26565.4%
  2. #203medium of 26559.5%
  3. #242none of 26543.8%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #140xhigh of 52376.7%
  2. #233medium of 52367.3%
  3. #378none of 52329.7%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #78xhigh of 945.0%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #28high of 8288.8%

Leader: Gemini 3.1 Pro · 98.1%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #54high of 11544.9%
  2. #85low of 11520.4%
  3. #109none of 1154.6%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #82high of 1161199

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #54xhigh of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #152xhigh of 21551.5%
  2. #167high of 21538.2%
  3. #176medium of 21533.0%
  4. #186low of 21518.3%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #150xhigh of 2165.7%
  2. #165high of 2163.6%
  3. #178medium of 2161.9%
  4. #182low of 2161.5%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #120xhigh of 5299.3%
  2. #152medium of 5295.1%
  3. #360none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #95high of 13577.9%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #60high of 8038.1%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #40xhigh of 1710.4%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #37xhigh of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #10none of 3510.6s
  2. #229medium of 3515.2s
  3. #330xhigh of 351103s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #60medium of 351178.8
  2. #66xhigh of 351172.3
  3. #67none of 351171.4

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #66xhigh of 1771.0s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #47xhigh of 17684.6

Leader: Muse Spark 1.1 · 204.3