Glimmer Index
Plus $4/mo

Grok 4.6

xAI · Released Aug 12, 2026 · Closed weights

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

Strongest at
Coding
Top 28% of the past year's models · 3 of 7 benchmarks
Price per 1M tokens
$2 / $6
input / output · xAI
Context window
500K
tokens in · 500K out
Since the last one
35 days
after Grok 4.5
Lab announcement ↗Open in the timeline

Capability profile

Scored against 91 models released in the past year. 50 is the average model; further out is better.

This modelGrok 4.5Median of the past year
5090Median of the past yearGrok 4.5Coding: 60 · Top 28%Writing: 44 · Better than 20%Reading & documents: 53 · Top 46%Reasoning: 66 · Top 30%Math: 60 · Top 42%Science: 58 · Better than 21%Visual reasoning: 51 · Better than 40%Computer use: 68 · Top 48%CodingWritingReadingReasoningMathScienceVisionComputer use
Coding60+9.8Top 28%
Writing44+0.4Better than 20%
Reading & documents53+4.0Top 46%
Reasoning66+2.9Top 30%
Math60+5.0Top 42%
Science58−1.2Better than 21%
Visual reasoning51+5.8Better than 40%
Computer use68+8.4Top 48%
Where these scores come from

Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow dot rests on a single benchmark.

Price against capability

The shaded corner holds anything better and cheaper. Prices blend input and output 3 to 1.

5 models from the past year score higher on Coding for less: DeepSeek V4.1 Flash, Muse Spark 1.3, DeepSeek V3.2 and 2 more.

$0.3$1$3$10020406080Claude Haiku 5.5: 60, $0.2 per 1MMistral Large 4: 56, $2.06 per 1MGemini 4 Argon: 65, $4 per 1MGPT-6.1 Sol: 64, $4 per 1MClaude Sonnet 5.5: 71, $4 per 1MGPT-6 Sol: 62, $4 per 1MGPT-6 Luna: 55, $0.2 per 1MClaude Opus 5.5: 79, $8 per 1MGrok 4.7: 59, $3 per 1MDeepSeek V4.1 Flash: 72, $0.21 per 1MGPT-6 Astra: 73, $20 per 1MMuse Spark 1.3: 69, $2 per 1MGemini 3.8 Flash: 57, $1.5 per 1MClaude Fable 5.1: 85, $20 per 1MGLM-5.3-Flash: 54, $0.24 per 1MDeepSeek V4 Flash Vision Exp: 55, $0.32 per 1MQwen3.8 27B: 60, $1.12 per 1MGLM-5.3: 60, $2.15 per 1MGemini 3.7 Flash: 59, $1.5 per 1MDeepSeek V4 Pro 0813: 49, $0.99 per 1MMuse Spark 1.2: 53, $2 per 1MQwen3.8 Max: 55, $3 per 1MDeepSeek V4 Flash 0731: 38, $0.15 per 1MClaude Opus 5: 69, $10 per 1MGemini 3.6 Flash: 44, $1.5 per 1MGemini 3.5 Flash Lite: 41, $0.85 per 1MKimi K3: 63, $6 per 1MGPT-5.6 Terra: 58, $4.5 per 1MGPT-5.6 Sol: 68, $8 per 1MGPT-5.6 Luna: 56, $0.45 per 1MClaude Sonnet 5: 60, $4 per 1MGLM-5.2: 48, $2.15 per 1MKimi K2.7 Code: 36, $1.71 per 1MClaude Fable 5: 77, $20 per 1MQwen3.7 Plus: 25, $0.7 per 1MClaude Opus 4.8: 62, $10 per 1MQwen3.7 Max: 48, $3.75 per 1MGemini 3.5 Flash: 47, $3.38 per 1MDeepSeek V4 Pro: 41, $1.19 per 1MDeepSeek V4 Flash: 23, $0.18 per 1MGPT-5.5: 58, $11.2 per 1MQwen3.6 27B: 29, $1.35 per 1MKimi K2.6: 52, $1.71 per 1MGrok 4.3: 1, $1.56 per 1MGrok Build 0.1: 29, $1.25 per 1MClaude Opus 4.7: 60, $10 per 1MMuse Spark 1.1: 52, $2 per 1MGLM-5.1: 55, $2.15 per 1MQwen3.6 Plus: 39, $1.12 per 1MGPT-5.4 nano: 36, $0.46 per 1MGPT-5.4 mini: 37, $1.69 per 1MGPT-5.4: 52, $5.62 per 1MGemini 3.1 Pro Preview: 38, $4.5 per 1MClaude Sonnet 4.6: 35, $6 per 1MGLM-5: 52, $1.55 per 1MGPT-5.3 Codex: 56, $4.81 per 1MClaude Opus 4.6: 54, $10 per 1MKimi K2.5: 54, $1 per 1MGemini 3 Flash Preview: 49, $1.12 per 1MGPT-5.2 Codex: 55, $4.81 per 1MGPT-5.2: 57, $4.81 per 1MDeepSeek V3.2: 68, $0.32 per 1MClaude Opus 4.5: 59, $10 per 1MGPT-5.1: 46, $3.44 per 1MGrok 4.5: 50, $3 per 1MGrok 4.6: 60, $3 per 1MGrok 4.6Price per 1M tokens →↑ Coding$1$10020406080Claude Haiku 5.5: 60, $0.2 per 1MMistral Large 4: 56, $2.06 per 1MGemini 4 Argon: 65, $4 per 1MGPT-6.1 Sol: 64, $4 per 1MClaude Sonnet 5.5: 71, $4 per 1MGPT-6 Sol: 62, $4 per 1MGPT-6 Luna: 55, $0.2 per 1MClaude Opus 5.5: 79, $8 per 1MGrok 4.7: 59, $3 per 1MDeepSeek V4.1 Flash: 72, $0.21 per 1MGPT-6 Astra: 73, $20 per 1MMuse Spark 1.3: 69, $2 per 1MGemini 3.8 Flash: 57, $1.5 per 1MClaude Fable 5.1: 85, $20 per 1MGLM-5.3-Flash: 54, $0.24 per 1MDeepSeek V4 Flash Vision Exp: 55, $0.32 per 1MQwen3.8 27B: 60, $1.12 per 1MGLM-5.3: 60, $2.15 per 1MGemini 3.7 Flash: 59, $1.5 per 1MDeepSeek V4 Pro 0813: 49, $0.99 per 1MMuse Spark 1.2: 53, $2 per 1MQwen3.8 Max: 55, $3 per 1MDeepSeek V4 Flash 0731: 38, $0.15 per 1MClaude Opus 5: 69, $10 per 1MGemini 3.6 Flash: 44, $1.5 per 1MGemini 3.5 Flash Lite: 41, $0.85 per 1MKimi K3: 63, $6 per 1MGPT-5.6 Terra: 58, $4.5 per 1MGPT-5.6 Sol: 68, $8 per 1MGPT-5.6 Luna: 56, $0.45 per 1MClaude Sonnet 5: 60, $4 per 1MGLM-5.2: 48, $2.15 per 1MKimi K2.7 Code: 36, $1.71 per 1MClaude Fable 5: 77, $20 per 1MQwen3.7 Plus: 25, $0.7 per 1MClaude Opus 4.8: 62, $10 per 1MQwen3.7 Max: 48, $3.75 per 1MGemini 3.5 Flash: 47, $3.38 per 1MDeepSeek V4 Pro: 41, $1.19 per 1MDeepSeek V4 Flash: 23, $0.18 per 1MGPT-5.5: 58, $11.2 per 1MQwen3.6 27B: 29, $1.35 per 1MKimi K2.6: 52, $1.71 per 1MGrok 4.3: 1, $1.56 per 1MGrok Build 0.1: 29, $1.25 per 1MClaude Opus 4.7: 60, $10 per 1MMuse Spark 1.1: 52, $2 per 1MGLM-5.1: 55, $2.15 per 1MQwen3.6 Plus: 39, $1.12 per 1MGPT-5.4 nano: 36, $0.46 per 1MGPT-5.4 mini: 37, $1.69 per 1MGPT-5.4: 52, $5.62 per 1MGemini 3.1 Pro Preview: 38, $4.5 per 1MClaude Sonnet 4.6: 35, $6 per 1MGLM-5: 52, $1.55 per 1MGPT-5.3 Codex: 56, $4.81 per 1MClaude Opus 4.6: 54, $10 per 1MKimi K2.5: 54, $1 per 1MGemini 3 Flash Preview: 49, $1.12 per 1MGPT-5.2 Codex: 55, $4.81 per 1MGPT-5.2: 57, $4.81 per 1MDeepSeek V3.2: 68, $0.32 per 1MClaude Opus 4.5: 59, $10 per 1MGPT-5.1: 46, $3.44 per 1MGrok 4.5: 50, $3 per 1MGrok 4.6: 60, $3 per 1MGrok 4.6Price per 1M tokens →↑ Coding

OpenRouter $2 / $6 · xAI $2 / $6 · Cached input $0.5

Since Grok 4.5

11 releases in the Grok 4.7 line.

Grok 4.1Nov 17, 2025112dGrok 4.20 (Non-Reasoning)Mar 9, 20260dGrok 4.20 (Reasoning)Mar 9, 202639dGrok 4.3Apr 17, 202682dGrok 4.5Jul 8, 202635dGrok 4.6Aug 12, 202640dGrok 4.7Sep 21, 2026
Released35 days later
Price in / out$2 / $6same price
Context500Ksame
Coding60+9.8
Writing44+0.4
Reading & documents53+4.0
Reasoning66+2.9
Math60+5.0
Science58−1.2
Visual reasoning51+5.8
Computer use68+8.4

A newer release is out: Grok 4.7.

ECI STANDING#28 of 270
SCORE156.57154.68–159.19 CI
FRONTIER LAGLaunched 6.2 months behindScores about what GPT-5.3 Codex did in February 2026.
SCORES LIKE THESE MODELSClaude Opus 4.7Anthropic · Apr 2026156.79GPT-6 LunaOpenAI · Sep 2026156.75GPT-5.6 LunaOpenAI · Jul 2026156.5GPT-5.2 ProOpenAI · Dec 2025156.33
Full Epoch Capabilities Index ranking ↗

Epoch benchmark boards

Best result on each board it has run. The tick marks the leader.

DTBench
97%#6 of 179
GPQA diamond
94%#12 of 234
SimpleBench
76%#7 of 89
OTIS Mock AIME 2024-2025
99%#19 of 216
APEX-Agents
65%#7 of 51
WeirdML
67%#24 of 141
FrontierCode
48%#10 of 46
ARC-AGI-2
67%#24 of 103
10 more boards
Mystery Game Puzzles
34%#24 of 88
ARC-AGI
88%#34 of 107
SimpleQA Verified
49%#30 of 85
ProofBench
51%#29 of 81
FrontierMath-Tiers-1-3-v2-Private
66%#34 of 90
FrontierMath-Tier-4-v2-Private
32%#33 of 72
EBR-bench
30%#14 of 28
Furniture Assembly
40%#18 of 35
Chess Puzzles
33%#49 of 93
FrontierSWE
25%#14 of 21

xAI's past year

19 release days in the past year, about one every 19 days. The next is expected around Nov 10, 2026. Forecasts ↗

NovDecJanFebMarAprMayJunJulAugSepOctNov

Specifications

RELEASE DATEAug 12, 2026
WEIGHTSClosed weights
CONTEXT WINDOW500K
MAX OUTPUT500K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext, image/jpeg, image/png
OUTPUTStext

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.