priorsBuilder

OpenAI · released 2026-07-09

GPT-5.6 Terra

Measured on 97 benchmarks across 6 reasoning efforts.

General frontier

48.7

#16 of 32 models · best at max

Reasoning efforts in your mix

max48.7#54 of 128
xhigh44.5#72 of 128
high42.1#80 of 128
medium35.4#107 of 128
low30.3#114 of 128
none24.1#122 of 128

Your mix’s benchmarks

8 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #59max of 58742.9%
  2. #72xhigh of 58741.9%
  3. #96high of 58738.5%
  4. #135medium of 58733.3%
  5. #154low of 58729.2%
  6. #284none of 58711.4%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #132max of 5260.1
  2. #147xhigh of 526-3.0
  3. #148high of 526-3.5
  4. #159medium of 526-5.1
  5. #167low of 526-6.8
  6. #249none of 526-23.2

Leader: Opus 5.5 · 46.4

reasoning

ARC-AGI-3

57 results
  1. #31max of 570.8%
  2. #33xhigh of 570.7%
  3. #37high of 570.5%
  4. #54medium of 570.1%
  5. #57low of 570.0%

Leader: GPT-6 Astra · 99.9%

reasoning

BullshitBench v2

196 results
  1. #67max of 19654.0%
  2. #83low of 19647.0%

Leader: Opus 4.8 · 95.0%

coding

DeepSWE v1.1

70 results
  1. #14max of 7069.6%
  2. #33xhigh of 7060.2%
  3. #44high of 7053.8%
  4. #62medium of 7035.1%
  5. #67low of 7024.1%

Leader: GPT-6 Astra · 74.1%

math

FrontierMath Tier 4 (v2)

70 results
  1. #18max of 7070.7%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #54xhigh of 9748.9%

Leader: Opus 5.5 · 88.4%

agentic

Terminal-Bench 4.0

35 results
  1. #27max of 3521.5%

Leader: Opus 5.5 · 64.8%

All 97 benchmarks

show 89 more

agentic

AA-Briefcase v1.1

224 results
  1. #65max of 2241334
  2. #66xhigh of 2241333
  3. #87high of 2241202
  4. #113medium of 2241039
  5. #115low of 2241014
  6. #125none of 224947

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #31xhigh of 500.9%

Leader: Opus 5.5 · 15.5%

agentic

APEX-Agents-AA

33 results
  1. #4max of 3338.9%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench (Zapier)

115 results
  1. #30max of 11523.6%
  2. #54xhigh of 11514.8%
  3. #66high of 11511.7%
  4. #81medium of 1158.1%
  5. #84low of 1157.5%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #36max of 21959.6%
  2. #84xhigh of 21947.1%
  3. #90high of 21942.0%
  4. #109medium of 21933.5%
  5. #112low of 21929.1%
  6. #143none of 21912.5%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #32max of 5038.5%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #59max of 790.8%

Leader: Muse Spark 1.2 · 25.4%

agentic

ITBench-AA

45 results
  1. #5max of 4551.0%

Leader: GPT-5.6 Sol · 56.2%

agentic

Legal Research Bench

78 results
  1. #26max of 7841.3%

Leader: Muse Spark 1.3 · 55.3%

agentic

SkillsBench

34 results
  1. #10max of 3458.9%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Tax Agent Bench

69 results
  1. #26max of 6930.0%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 2.1

18 results
  1. #11max of 1878.4%

Leader: GPT-6 Astra · 87.4%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #22max of 4722.7%

Leader: Opus 5.5 · 65.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #17max of 4010.0%

Leader: GPT-6 Astra · 62.9%

agentic

Vending-Bench 2

67 results
  1. #15max of 67$7,343

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #88max of 39386.3%
  2. #124xhigh of 39380.4%
  3. #132high of 39378.4%
  4. #149medium of 39372.8%
  5. #182low of 39360.5%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #29max of 20640.2%
  2. #68xhigh of 20629.7%
  3. #73high of 20628.7%
  4. #80medium of 20625.6%
  5. #103low of 20618.8%
  6. #116none of 20615.7%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #29xhigh of 581540

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #47xhigh of 1221522

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #13max of 7747.8%

Leader: Sonnet 5.5 · 69.8%

coding

FrontierCode 1.1 Extended

130 results
  1. #59max of 13055.8%
  2. #76xhigh of 13052.6%
  3. #85high of 13050.9%
  4. #95medium of 13047.7%
  5. #114low of 13037.8%

Leader: Opus 5.5 · 65.3%

coding

FrontierCode 1.1 Main

130 results
  1. #64max of 13041.3%
  2. #75xhigh of 13038.8%
  3. #83high of 13036.9%
  4. #95medium of 13033.9%
  5. #112low of 13024.1%

Leader: Opus 5.5 · 54.6%

coding

IOI

44 results
  1. #7max of 4487.6%

Leader: Gemini 4 · 100.0%

coding

LiveCodeBench (Vals)

127 results
  1. #27xhigh of 12785.9%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #19max of 6215.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #24max of 620.5%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #13max of 6272.3%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #53max of 22655.0%
  2. #82high of 22652.4%
  3. #83xhigh of 22652.3%
  4. #102medium of 22650.5%
  5. #109low of 22649.9%
  6. #140none of 22645.1%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #5max of 8595.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #15max of 7477.5%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #4xhigh of 38762.9%
  2. #11max of 38757.6%
  3. #13high of 38757.6%
  4. #38low of 38743.9%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench Science-AA

46 results
  1. #20max of 4613.8%

Leader: GPT-6 Astra · 63.3%

coding

Terminal-Bench v2.1-AA

238 results
  1. #17max of 23888.0%
  2. #45xhigh of 23880.1%
  3. #60high of 23875.7%
  4. #68medium of 23872.3%
  5. #89low of 23862.5%
  6. #105none of 23856.2%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #33max of 21635.4%
  2. #86xhigh of 21610.1%
  3. #117high of 2161.5%
  4. #120low of 2161.5%
  5. #125medium of 2161.0%
  6. #140none of 2160.5%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench 1-100

22 results
  1. #15max of 2214.8%

Leader: Opus 5.5 · 30.4%

coding

Vibe Code Bench v1.1

105 results
  1. #34max of 10574.6%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #18max of 12778.3%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #52max of 61042.1
  2. #76xhigh of 61038.0
  3. #92high of 61034.2
  4. #118medium of 61030.1
  5. #139low of 61027.5
  6. #216none of 61020.8

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #45xhigh of 2201466

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #53xhigh of 2201469

Leader: Gemini 4 · 1553

composite

Vals Index

47 results
  1. #22max of 4753.1%

Leader: Gemini 4 · 68.9%

composite

Vals Multimodal Index v1.2

33 results
  1. #14xhigh of 3365.1%

Leader: Fable 5 · 74.2%

cost

AA Intelligence Index Cost per Task

177 results
  1. #48none of 177$0.14
  2. #49low of 177$0.14
  3. #55medium of 177$0.18
  4. #75high of 177$0.34
  5. #98xhigh of 177$0.63
  6. #133max of 177$1.40

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #48none of 177$256
  2. #56low of 177$350
  3. #64medium of 177$447
  4. #85high of 177$768
  5. #106xhigh of 177$1,187
  6. #145max of 177$2,501

Leader: GPT-6 Luna · $10.63

creative

threejseval

34 results
  1. #20max of 341449
  2. #30low of 341172

Leader: Opus 5.5 · 2079

creative

VoxelBench (text)

55 results
  1. #12max of 551887

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #30xhigh of 11765.3%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #22max of 7466.2%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #25max of 7854.4%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #33xhigh of 21024.6%
  2. #38max of 21024.0%
  3. #59high of 21020.8%
  4. #77low of 21017.6%
  5. #84medium of 21017.0%
  6. #121none of 21011.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #59max of 2881451
  2. #62xhigh of 2881447
  3. #78high of 2881376
  4. #102medium of 2881264
  5. #134low of 2881108
  6. #140none of 2881097

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #25xhigh of 8467.3%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #6xhigh of 12576.2%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #57max of 39971.2%
  2. #96xhigh of 39966.3%
  3. #107high of 39964.4%
  4. #118medium of 39962.2%
  5. #126low of 39959.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #77max of 52646.8%
  2. #86xhigh of 52645.5%
  3. #87high of 52645.5%
  4. #91medium of 52644.6%
  5. #95low of 52643.7%
  6. #144none of 52636.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #368max of 52612.1%
  2. #384xhigh of 52611.0%
  3. #396medium of 52610.2%
  4. #397high of 52610.2%
  5. #400low of 52610.1%
  6. #499none of 5265.0%

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

knowledge

GPQA Diamond

539 results
  1. #35max of 53992.5%
  2. #55xhigh of 53990.8%
  3. #71high of 53989.6%
  4. #101medium of 53987.2%
  5. #144low of 53984.3%
  6. #254none of 53974.6%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #24xhigh of 12290.9%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #42xhigh of 9443.4%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #46xhigh of 9682.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #39xhigh of 12286.7%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #20max of 8186.5%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #42max of 26580.7%
  2. #57xhigh of 26579.5%
  3. #60high of 26579.1%
  4. #82medium of 26576.8%
  5. #89low of 26576.1%
  6. #164none of 26566.7%

Leader: Opus 5.5 · 87.7%

knowledge

Public Benefits Bench v1.1

50 results
  1. #28max of 5062.4%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #29max of 52383.0%
  2. #104xhigh of 52379.0%
  3. #124high of 52377.7%
  4. #166medium of 52374.0%
  5. #200low of 52371.3%
  6. #277none of 52358.7%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #13xhigh of 431472

Leader: Opus 5 · 1516

long-context

MLCR-AA

94 results
  1. #19max of 9431.7%
  2. #26xhigh of 9421.7%
  3. #57high of 9412.2%
  4. #59medium of 9412.2%
  5. #68low of 948.9%

Leader: Sonnet 5.5 · 75.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #10max of 11586.0%

Leader: GPT-6.1 Sol · 93.7%

math

ProofBench v1.1

52 results
  1. #19max of 5274.0%

Leader: Sonnet 5.5 · 100.0%

other

Arena Vision

116 results
  1. #37xhigh of 1161268

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #12max of 850.7%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #23max of 21596.5%
  2. #41xhigh of 21594.0%
  3. #56high of 21592.0%
  4. #111medium of 21577.0%
  5. #139low of 21560.2%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #33max of 21683.9%
  2. #45xhigh of 21674.2%
  3. #62high of 21667.1%
  4. #107medium of 21637.5%
  5. #125low of 21618.8%

Leader: GPT-6 Astra · 95.0%

reasoning

Blueprint-Bench 2

28 results
  1. #17max of 2830.8%

Leader: Gemini 4 · 54.4%

reasoning

CritPt

529 results
  1. #17max of 52930.0%
  2. #35xhigh of 52927.1%
  3. #52high of 52922.9%
  4. #77medium of 52917.4%
  5. #118low of 5299.4%
  6. #197none of 5292.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Furniture Assembly

31 results
  1. #9max of 3154.2%

Leader: Opus 5.5 · 83.3%

reasoning

Humanity's Sixth Sense

25 results
  1. #23max of 2522.7%

Leader: GPT-6 Astra · 53.6%

reasoning

LegalBench

135 results
  1. #24max of 13585.1%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #50high of 10265.3%
  2. #61low of 10260.9%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #33max of 8047.0%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #20max of 4741.5%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #26max of 1710.3%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #93max of 18199.5%

Leader: GPT-5 Pro · 100.0%

safety

CyberBench v1.1

45 results
  1. #18max of 4572.1%

Leader: Wonder · 80.4%

safety

SRE Bench

32 results
  1. #12max of 329.5%

Leader: GPT-6 Astra · 56.9%

speed

Latency (Time to First Token)

351 results
  1. #23none of 3510.7s
  2. #127low of 3511.7s
  3. #137medium of 3511.7s
  4. #242high of 3517.4s
  5. #309xhigh of 35143s
  6. #338max of 351129s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #107max of 351129.3
  2. #140xhigh of 351110.4
  3. #152medium of 351105.4
  4. #153high of 351105.0
  5. #157none of 351102.4
  6. #161low of 351101.2

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #128max of 1772.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #61max of 17679.0

Leader: Muse Spark 1.1 · 204.3