priorsBuilder

DeepSeek · released 2025-08-19

DeepSeek V3.1

Measured on 37 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. #235default of 58716.4%
  2. #336none of 5878.7%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #257default of 526-26.4
  2. #328none of 526-42.8

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #67none of 9740.0%

Leader: Opus 5.5 · 88.4%

All 37 benchmarks

show 34 more

agentic

AA-Briefcase v1.1

224 results
  1. #179default of 224458

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #172default of 2192.7%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #228default of 39337.4%
  2. #230none of 39337.1%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #94default of 20621.0%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #28default of 28279.8%
  2. #108none of 28257.7%

Leader: Gemini 3 Pro · 91.7%

coding

SciCode

226 results
  1. #184default of 22638.0%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #54none of 6322.5%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #106none of 38731.8%
  2. #116default of 38730.3%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #130default of 23844.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #173default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

WeirdML v2

127 results
  1. #94none of 12738.4%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #287default of 61014.8
  2. #298none of 61013.9

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #106none of 2201417

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #110none of 2201415

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #92none of 11751.5%

Leader: Opus 5 · 73.2%

economics

GDP.pdf

210 results
  1. #158default of 2105.4%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #196default of 288709

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #138default of 39957.0%
  2. #246none of 39941.2%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #187default of 52629.0%
  2. #249none of 52623.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #237default of 52625.2%
  2. #344none of 52614.3%

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

knowledge

CaseLaw (Vals)

53 results
  1. #39none of 5353.9%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #52default of 11882.7%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #199default of 53979.2%
  2. #248none of 53975.1%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #28default of 28585.1%
  2. #45none of 28583.6%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #223default of 52369.3%
  2. #313none of 52347.0%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #26default of 22889.7%
  2. #113none of 22853.7%

Leader: GPT-5.2 · 99.0%

other

Poker Agent

17 results
  1. #7none of 171058

Leader: GPT-5.2 · 1132

reasoning

CritPt

529 results
  1. #198default of 5292.0%
  2. #338none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

172 results
  1. #132none of 1723.7%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #153none of 18297.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #112none of 3511.5s
  2. #190default of 3512.7s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #123default of 351120.5
  2. #180none of 35194.2

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #39none of 1780.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #125none of 17648.0

Leader: Muse Spark 1.1 · 204.5