priorsBuilder

DeepSeek · released 2025-03-25

DeepSeek V3

Measured on 45 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. #466none of 5874.7%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #313none of 526-40.7

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #80none of 9727.2%

Leader: Opus 5.5 · 88.4%

All 45 benchmarks

show 42 more

agentic

AA-Briefcase v1.1

224 results
  1. #207none of 22478

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #198none of 2190.6%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #208none of 39347.1%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #189none of 2064.7%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #150none of 28240.5%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #96none of 12765.5%

Leader: Fable 5.1 · 90.5%

coding

SciCode

226 results
  1. #177none of 22639.0%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #193none of 38715.2%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #183none of 23816.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #192none of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #380none of 6109.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #148none of 2201358

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #137none of 2201373

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #14none of 177$0.02

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #6none of 177$25.37

Leader: GPT-6 Luna · $10.63

economics

CorpFin (Vals)

117 results
  1. #86none of 11754.7%

Leader: Opus 5 · 73.2%

economics

GDP.pdf

210 results
  1. #187none of 2101.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #257none of 28869

Leader: Opus 5.5 · 1866

economics

TaxEval (Vals)

125 results
  1. #78none of 12571.1%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #249none of 39941.0%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #219none of 52625.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #346none of 52614.1%

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

knowledge

GPQA Diamond

539 results
  1. #332none of 53965.5%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #100none of 12261.6%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #58none of 8082.0%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #89none of 12279.5%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #66none of 28581.9%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #343none of 52340.7%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #57none of 8252.2%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #132none of 22841.0%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #27none of 4888.6%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #41none of 16294.2%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #19none of 6292.1%

Leader: Opus 4.5 · 95.2%

reasoning

CritPt

529 results
  1. #388none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #79none of 13580.8%

Leader: Fable 5 · 88.6%

reasoning

SimpleQA Verified

47 results
  1. #33none of 4727.4%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

172 results
  1. #121none of 1723.0%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #161none of 18297.1%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #88none of 3511.1s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #203none of 35182.1

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #58none of 1780.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #165none of 17627.8

Leader: Muse Spark 1.1 · 204.5