priorsBuilder

OpenAI · released 2025-08-07

GPT-5 Nano

Measured on 48 benchmarks.

General frontier

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

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #323high of 5879.5%
  2. #334medium of 5878.7%
  3. #533minimal of 5874.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #255medium of 526-25.8
  2. #267high of 526-28.7
  3. #465minimal of 526-64.1

Leader: Opus 5.5 · 46.4

math

FrontierMath Tier 4 (v2)

70 results
  1. #65high of 702.4%

Leader: GPT-6.1 Sol · 100.0%

All 48 benchmarks

show 45 more

agentic

Terminal-Bench 2.0

40 results
  1. #36high of 4021.8%

Leader: GPT-5.5 · 84.7%

agentic

τ²-Bench Telecom

393 results
  1. #233high of 39336.5%
  2. #256medium of 39330.4%
  3. #284minimal of 39325.7%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #30high of 28278.9%
  2. #41medium of 28276.3%
  3. #134minimal of 28247.0%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #88high of 12770.2%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #182medium of 38717.4%
  2. #207high of 38712.1%
  3. #253minimal of 3876.8%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #95high of 12738.1%
  2. #112low of 12725.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #313high of 61013.0
  2. #322medium of 61012.5
  3. #475minimal of 6107.1

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #163high of 2201337

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #167high of 2201324

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #72high of 72607

Leader: GPT-6 Astra Pro · 2281

economics

MortgageTax (Vals)

84 results
  1. #71high of 8453.6%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #97high of 12567.4%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #85high of 39967.6%
  2. #101medium of 39965.9%
  3. #325minimal of 39932.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #307high of 52619.1%
  2. #346medium of 52617.6%
  3. #435minimal of 52613.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #128medium of 52647.4%
  2. #151high of 52641.0%
  3. #378minimal of 52611.2%

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

knowledge

CaseLaw (Vals)

53 results
  1. #44high of 5352.6%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #62high of 11881.2%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #309high of 53967.6%
  2. #315medium of 53967.0%
  3. #445minimal of 53942.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #97high of 12263.4%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #87high of 9430.4%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #23high of 8093.3%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #76high of 9672.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #99high of 12276.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #119high of 28578.0%
  2. #129medium of 28577.2%
  3. #229minimal of 28555.6%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #62high of 8170.9%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #197high of 26561.0%
  2. #207medium of 26558.2%
  3. #256minimal of 26531.8%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #322high of 52345.0%
  2. #328medium of 52343.7%
  3. #417minimal of 52320.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #45high of 8281.2%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #48high of 22883.7%
  2. #67medium of 22878.3%
  3. #161minimal of 22827.3%

Leader: GPT-5.2 · 99.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #86high of 11520.0%
  2. #108low of 1156.0%
  3. #111minimal of 1151.8%

Leader: GPT-6.1 Sol · 93.7%

math

MATH 500 (Vals)

48 results
  1. #15high of 4893.8%

Leader: Gemini 3 Pro · 96.4%

math

MGSM (Vals)

62 results
  1. #40high of 6289.3%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #98high of 1161146

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #45high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #185medium of 21520.7%
  2. #188high of 21516.7%
  3. #210low of 2154.0%
  4. #213minimal of 2151.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #170high of 2162.6%
  2. #191medium of 2160.9%
  3. #213low of 2160.0%
  4. #214minimal of 2160.0%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #344high of 5290.0%
  2. #351medium of 5290.0%
  3. #448minimal of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #133high of 13550.1%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #75high of 8030.4%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #17high of 1710.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #57high of 18199.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #24minimal of 3510.7s
  2. #301medium of 35132s
  3. #316high of 35158s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #33high of 351208.5
  2. #51minimal of 351192.2
  3. #55medium of 351187.9

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #86high of 1771.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #20high of 176108.6

Leader: Muse Spark 1.1 · 204.3