priorsBuilder

OpenAI · released 2025-08-05

gpt-oss-120b

Measured on 59 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. #210high of 58719.6%
  2. #397low of 5875.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #368high of 526-49.3
  2. #400low of 526-53.5

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #168low of 19612.0%
  2. #190high of 1965.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #90high of 9722.1%

Leader: Opus 5.5 · 88.4%

All 59 benchmarks

show 55 more

agentic

AA-Briefcase v1.1

224 results
  1. #213high of 2240

Leader: Sonnet 5.5 · 1823

agentic

APEX-Agents-AA

33 results
  1. #30high of 333.1%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench (Zapier)

115 results
  1. #114high of 1150.1%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #213high of 2190.2%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #48high of 5025.5%

Leader: Fable 5 · 51.1%

agentic

ITBench-AA

45 results
  1. #43high of 455.6%

Leader: GPT-5.6 Sol · 56.2%

agentic

Terminal-Bench 2.0

40 results
  1. #37high of 4018.7%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #65high of 67$-21.53

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #172high of 39365.8%
  2. #216low of 39345.0%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #132high of 20612.8%
  2. #200low of 2062.9%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #7high of 28287.8%
  2. #60low of 28270.7%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #51high of 12783.2%

Leader: Fable 5.1 · 90.5%

coding

SciCode

226 results
  1. #196high of 22634.0%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #84high of 8533.6%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #56high of 6319.1%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #151high of 38723.5%
  2. #261low of 3875.3%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #166high of 23826.2%
  2. #186low of 23813.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #184high of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

WeirdML v2

127 results
  1. #67high of 12748.2%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #340high of 61011.6
  2. #369low of 61010.2

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #152high of 2201352

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #164high of 2201326

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #40high of 177$0.11

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #29high of 177$122

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #69high of 72824

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #80high of 11758.2%

Leader: Opus 5 · 73.2%

economics

GDP.pdf

210 results
  1. #167high of 2104.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #203high of 288608
  2. #253low of 288172

Leader: Opus 5.5 · 1866

economics

TaxEval (Vals)

125 results
  1. #73high of 12571.6%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #75high of 39969.0%
  2. #129low of 39958.3%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #271high of 52621.8%
  2. #299low of 52619.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #414high of 5269.2%
  2. #433low of 5268.6%

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

knowledge

CaseLaw (Vals)

53 results
  1. #50high of 5348.8%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #51high of 11882.8%
  2. #71low of 11880.1%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #211high of 53978.2%
  2. #313low of 53967.2%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #72high of 12278.5%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #36high of 8091.4%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #91high of 12279.2%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #84high of 28580.8%
  2. #124low of 28577.5%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #302high of 52352.0%
  2. #318low of 52346.0%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #88high of 941.1%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #18high of 8292.6%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #15high of 22893.4%
  2. #91low of 22866.7%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #7high of 4894.8%

Leader: Gemini 3 Pro · 96.4%

math

MGSM (Vals)

62 results
  1. #21high of 6292.0%

Leader: Opus 4.5 · 95.2%

other

Poker Agent

17 results
  1. #13high of 171015

Leader: GPT-5.2 · 1132

reasoning

CritPt

529 results
  1. #229high of 5291.1%
  2. #380low of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #102high of 13575.9%

Leader: Fable 5 · 88.6%

reasoning

SimpleQA Verified

47 results
  1. #39high of 4713.1%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #153high of 1716.6%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #170high of 18196.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #38high of 3510.8s
  2. #39low of 3510.8s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #19low of 351246.5
  2. #22high of 351237.3

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #11high of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #5high of 176141.0

Leader: Muse Spark 1.1 · 204.3