Skip to content
Model Pareto

Grok 4.6

SpaceXAI (xAI)Proprietaryx.ai ↗
Compare with nearest rivalsCompare with…
Input
$2.00/M tok
Output
$6.00/M tok
Blended
$3.00/M tok · 3:1
Speed
60tok/s
Context
500Ktokens

Previous generation.

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#3 of 14 (estimated)~82.8%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Grok 4.6Estimated82.8%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#7 of 19 (estimated)~64.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #6Hy4 preview65.7%
  4. ~#7Grok 4.6Estimated64.1%
  5. #7GPT-5.6 Terra63.4%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#3 of 20 (estimated)~90.8%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. ~#3Grok 4.6Estimated90.8%
  4. #3Qwen3.8 27B90.3%
No published score — estimated from related benchmarks

Writing & chat

IFBenchEstimated
~#20 of 126 (estimated)~74.7%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. #19GPT-5.3 Codex75.4%
  4. ~#20Grok 4.6Estimated74.7%
  5. #20Command A+73.9%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~89.6%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Grok 4.6Estimated89.6%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#18 of 531447 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #18Claude Sonnet 51447
  4. #18Grok 4.61447
  5. #20Gemini 3.5 Flash-Lite1445
lmarena.ai · 2026-09-24
LMArena Text (Elo)Verified
#22 of 531453 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #19Qwen3.7 Plus1456
  4. #22Grok 4.61453
  5. #23Gemma 4 31B1451
lmarena.ai · 2026-09-25
EQ-Bench Creative Writing v3 (Elo)Estimated
~#10 of 26 (estimated)~1897 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #9Muse Spark 1.31906
  4. ~#10Grok 4.6Estimated1897
  5. #10GPT-5.6 Terra1855
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Grok 4.6Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
MMMU-ProEstimated
~#10 of 77 (estimated)~81.5%
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
  3. #9Intern-S2-397B81.7%
  4. ~#10Grok 4.6Estimated81.5%
  5. #10GPT-5.6 Terra80.7%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~81.8%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Grok 4.6Estimated81.8%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~88.2%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Grok 4.6Estimated88.2%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.8%
  1. #1Inkling97.1%
  2. ~#2Grok 4.6Estimated96.8%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~97.7%
  1. #1Step 3.7 Flash98.5%
  2. ~#2Grok 4.6Estimated97.7%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 12 (estimated)~82.4%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Grok 4.6Estimated82.4%
  4. #3Nex-N2.5-Pro82.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~56.6%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Grok 4.6Estimated56.6%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#6 of 18 (estimated)~89.6%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #5Nex-N2.5-Pro89.7%
  4. ~#6Grok 4.6Estimated89.6%
  5. #6Step 5 Preview88.7%
No published score — estimated from related benchmarks