priorsBuilder

DeepSeek · released 2025-12-01

DeepSeek V3.2

Measured on 47 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. #156default of 58728.7%
  2. #288none of 58711.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #227default of 526-17.7
  2. #350none of 526-46.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #165high of 19613.0%
  2. #173none of 19610.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #51high of 9752.6%

Leader: Opus 5.5 · 88.4%

All 47 benchmarks

show 43 more

agentic

APEX-Agents-AA

33 results
  1. #24default of 3314.5%

Leader: Gemini 3.5 Flash · 47.1%

agentic

Terminal-Bench 2.0

40 results
  1. #23high of 4039.6%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #54high of 67$1,034

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #62default of 39390.6%
  2. #131none of 39378.9%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #94high of 1221362

Leader: Opus 5.5 · 1813

coding

LiveCodeBench

282 results
  1. #3default of 28289.6%
  2. #103none of 28259.3%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #66high of 12780.7%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #67high of 8567.6%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #40high of 6336.0%
  2. #41none of 6334.8%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #77default of 38735.6%
  2. #100none of 38732.6%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #126default of 23846.8%

Leader: Fable 5.1 · 91.4%

coding

Vibe Code Bench v1.1

105 results
  1. #92high of 1055.1%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #69high of 12746.7%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #207default of 61021.5
  2. #272none of 61016.0

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #99high of 2201425

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #97high of 2201428

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #62high of 721084

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #94high of 11751.0%
  2. #98none of 11747.9%

Leader: Opus 5 · 73.2%

economics

GDPval-AA v2.1

288 results
  1. #198default of 288691

Leader: Opus 5.5 · 1866

economics

TaxEval (Vals)

125 results
  1. #93high of 12568.2%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #111default of 39963.9%
  2. #178none of 39949.0%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #136default of 52637.8%
  2. #241none of 52624.0%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #282default of 52619.2%
  2. #448none of 5267.9%

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

knowledge

CaseLaw (Vals)

53 results
  1. #34high of 5355.4%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #24default of 11888.4%
  2. #53none of 11882.7%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #104default of 53987.1%
  2. #247none of 53975.1%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #69high of 12280.3%
  2. #77none of 12276.3%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #20high of 8093.9%
  2. #46none of 8089.5%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #59high of 12284.9%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #17default of 28586.3%
  2. #41none of 28583.7%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #179default of 52373.3%
  2. #320none of 52345.7%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #39high of 8284.6%
  2. #54none of 8264.8%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #5default of 22896.7%
  2. #103none of 22859.0%

Leader: GPT-5.2 · 99.0%

math

MGSM (Vals)

62 results
  1. #30high of 6290.9%

Leader: Opus 4.5 · 95.2%

other

Poker Agent

17 results
  1. #4high of 171090

Leader: GPT-5.2 · 1132

reasoning

ARC-AGI-1

215 results
  1. #144high of 21557.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #163high of 2164.0%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #136default of 5297.4%
  2. #209none of 5291.4%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #101high of 13576.1%

Leader: Fable 5 · 88.6%

reliability

Tool-call error rate

171 results
  1. #89high of 1711.4%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #164high of 18196.8%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #129high of 1772.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #168high of 17625.0

Leader: Muse Spark 1.1 · 204.3