Grok 4.6
- Input
- $2.00/M tok
- Output
- $6.00/M tok
- Blended
- $3.00/M tok · 3:1
- Speed
- 56tok/s
- Context
- 500Ktokens
- Cost per task
- ~$2.5/taskest.
Previous generation.
Rankings
Coding
Verified#36 / 137rank by quality63.3±4.5quality / 1004/7 benchmarks measuredWriting & chat
Verified#32 / 162rank by quality68.4±6.0quality / 1002/5 benchmarks measuredVision
Verified#36 / 98rank by quality63.1±7.4quality / 1002/6 benchmarks measuredHard reasoning
Verified#22 / 218rank by quality77.0±3.7quality / 1003/4 benchmarks measuredAgents
Verified#13 / 187rank by quality81.6±5.9quality / 1003/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#3 of 21 (estimated)~83.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#9 of 24 (estimated)~65.3%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #8Hy4 preview65.7%
- ~#9Grok 4.6Estimated65.3%
- #9GPT-5.6 Terra63.4%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#21 of 4564.9%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #20Gemini 3.8 Flash65.8%
- #21Grok 4.664.9%
- #22Claude Fable 5.164.3%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#10 of 28 (estimated)~82.8%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10Grok 4.6Estimated82.8%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
Writing & chat
IFBenchEstimated
~#36 of 140 (estimated)~70.9%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #35NVIDIA Nemotron 3 Nano 30B A3B71.1%
- ~#36Grok 4.6Estimated70.9%
- #36Nemotron 3.5 Super VL70.9%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#19 of 561447 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #19Claude Sonnet 51447
- #19Grok 4.61447
- #21Gemini 3.5 Flash-Lite1445
lmarena.ai · 2026-09-24
EQ-Bench Creative Writing v3 (Elo)Estimated
~#10 of 26 (estimated)~1900 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #9Muse Spark 1.31906
- ~#10Grok 4.6Estimated1900
- #10GPT-5.6 Terra1855
No published score — estimated from related benchmarks
Vision
MMMU-ProEstimated
~#22 of 88 (estimated)~78.6%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #20Ling-3.0-flash-VL79.0%
- ~#22Grok 4.6Estimated78.6%
- #22MiniMax-M378.6%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#6 of 12 (estimated)~81.9%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #5MiniMax-M3.1-Flash82.5%
- ~#6Grok 4.6Estimated81.9%
- #6Nemotron 3.5 Super VL80.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~88.1%
No published score — estimated from related benchmarks
Hard reasoning
Humanity's Last ExamVerified
#22 of 19844.1%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #21Claude Haiku 5.544.4%
- #22Grok 4.644.1%
- #23Muse Spark Open43.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#4 of 34 (estimated)~96.6%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #3Inkling97.1%
- ~#4Grok 4.6Estimated96.6%
- #4Ternary Bonsai 2 27B95.8%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#3 of 120 (estimated)~96.5%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- ~#3Grok 4.6Estimated96.5%
- #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#4 of 15 (estimated)~82.1%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~56.6%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#6 of 22 (estimated)~89.6%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #5Nex-N2.5-Pro89.7%
- ~#6Grok 4.6Estimated89.6%
- #6Step 5 Preview88.7%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#13 of 911632 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #12GLM-5.3 Flash1644
- #13Grok 4.61632
- #14Qwen3.8 Flash-Next1612
artificialanalysis.ai · 2026-09-24