THE SCOREBOARD FOR WHAT'S NEXTAI + QUANTUM, SCORED. COMPARED. EXPLAINED.
AIQUANTUMSCORE.

xAI / Grok

Grok 4.5

Version grok.4.5 · Released 2026-07-16 · Available

Compare this model ↗
44QUANTUM SCORE

Explore xAI history →

Coding0
Reasoning90
Math82
Research—
Agents32
Multimodal—
Speed—
Value39

01 / EVIDENCE

Benchmark breakdown

BenchmarkVersionMethodConfigurationResultTest dateVerifiedSource typeSource
CursorBench v3.2CursorBench v3.2Publisher-reported configuration; see source—66.7 %2026-08-122026-09-29provider first partyView source ↗
DeepSWE v1.1DeepSWE v1.1Publisher-reported configuration; see source—54 %2026-08-122026-09-29provider first partyView source ↗
APEX-AgentsAPEX-AgentsPublisher-reported configuration; see source—47.1 %2026-08-122026-09-29provider first partyView source ↗
Terminal-Bench v3.0Terminal-Bench v3.0Publisher-reported configuration; see source—15.7 %2026-08-122026-09-29provider first partyView source ↗
FrontierCode v1.1 ExtendedFrontierCode v1.1 ExtendedPublisher-reported configuration; see source—56.6 %2026-08-122026-09-29provider first partyView source ↗
GDPVal-AA v2GDPVal-AA v2Publisher-reported configuration; see source—1526 Elo2026-08-122026-09-29provider first partyView source ↗
SkillsBench Vals OpenHands with skillsVals 2026-09-27Vals OpenHands harness with skills—66.03 %2026-09-272026-09-29independent labView source ↗
LiveBench code_completion2026-06-25Public table; published model effort variantgrok-4.569.565 %not published2026-09-30benchmark maintainerView source ↗
LiveBench code_generation2026-06-25Public table; published model effort variantgrok-4.567.606 %not published2026-09-30benchmark maintainerView source ↗
LiveBench javascript2026-06-25Public table; published model effort variantgrok-4.572.727 %not published2026-09-30benchmark maintainerView source ↗
LiveBench AMPS_Hard2026-06-25Public table; published model effort variantgrok-4.599 %not published2026-09-30benchmark maintainerView source ↗
LiveBench olympiad2026-06-25Public table; published model effort variantgrok-4.589.239 %not published2026-09-30benchmark maintainerView source ↗
LiveBench theory_of_mind2026-06-25Public table; published model effort variantgrok-4.582.692 %not published2026-09-30benchmark maintainerView source ↗
LiveBench zebra_puzzle2026-06-25Public table; published model effort variantgrok-4.594 %not published2026-09-30benchmark maintainerView source ↗

02 / COST

Price & speed

Input / 1M tokens $2.00

Output / 1M tokens $6.00

Cached input / 1M —

Batch input / 1M —

Batch output / 1M —

Speed No comparable observation yet

Price verified 2026-09-29

Price scope Standard short-context rate; long-context and fast rates differ

Price source Official pricing ↗

02A / PERFORMANCE

Measured speed

No sourced speed measurement at a stated effort level yet.

03 / PROFILE

Capabilities

visiontool use

04 / CONTEXT

Strengths & limitations

Coverage: 73% · Moderate confidence · 14 observations · 3 source domains (2 independent).

05 / HISTORY

Version & price history

Version grok.4.5 · released 2026-07-16.

2026-09-29: $2.00 input / $6.00 output per 1M tokens · Price source ↗

06 / SOURCES

Source records

DATED EVIDENCE

History

Standard API price history

2026-09-292026-09-29
  • 2026-09-29: 3 USD / 1M · 75% input / 25% output USD per 1M · source ↗

One observation; no trend can be inferred.

CursorBench v3.2 / CursorBench v3.2 / %

2026-08-122026-08-12
  • 2026-08-12: 66.7 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

DeepSWE v1.1 / DeepSWE v1.1 / %

2026-08-122026-08-12
  • 2026-08-12: 54 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

APEX-Agents / APEX-Agents / %

2026-08-122026-08-12
  • 2026-08-12: 47.1 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

Terminal-Bench v3.0 / Terminal-Bench v3.0 / %

2026-08-122026-08-12
  • 2026-08-12: 15.7 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

FrontierCode v1.1 Extended / FrontierCode v1.1 Extended / %

2026-08-122026-08-12
  • 2026-08-12: 56.6 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

GDPVal-AA v2 / GDPVal-AA v2 / Elo

2026-08-122026-08-12
  • 2026-08-12: 1,526 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

SkillsBench Vals OpenHands with skills / Vals 2026-09-27 / %

2026-09-272026-09-27
  • 2026-09-27: 66.03 result · Vals OpenHands harness with skills · source ↗

One observation; no trend can be inferred.

LiveBench code_completion / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 69.565 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench code_generation / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 67.606 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench javascript / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 72.727 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench AMPS_Hard / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 99 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench olympiad / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 89.239 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench theory_of_mind / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 82.692 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench zebra_puzzle / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 94 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

agents category score history

2026-09-302026-09-30
  • 2026-09-30: 4 score · Scoring 3.0.0

One observation; no trend can be inferred.

07 / EXPLORE

Similar models