Noometry

xAI, proprietary

Grok 4.3

Grok 4.3 by xAI ranks 86th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.8. Its strongest category is knowledge, where it ranks 62nd. API pricing starts at $1.25 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#86 of 354
Index score
43.8
Evidence
Confirmed 40 results
Provider
xAI
Released
April 17, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
30K
Input price
$1.25 / M
Output price
$2.50 / M
Blended price
$1.56 / M
Output speed
Not measured
Value
#137 of 219
Knowledge cutoff
Unknown
Input
text, image, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 41.6
  2. Agentic & Tool Use 27.7
  3. Reasoning 35.9
  4. Math 46.0
  5. Knowledge 52.5
  6. Multimodal 31.6
  7. Multilingual 50.5
  8. Instruction Following 72.1
  9. Long Context 42.5
  10. Writing & Preference 58.5
CategoryScoreRankResults
Coding41.6#1214
Agentic & Tool Use27.7#991
Reasoning35.9#686
Math46.0#745
Knowledge52.5#623
Multimodal31.6#1042
Multilingual50.5#1201
Instruction Following72.1#1401
Long Context42.5#1231
Writing & Preference58.5#1184

Strengths and weaknesses

Categories where Grok 4.3 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Reasoning35.9+12.3#68 of 350, top 20%
Knowledge52.5+15.2#62 of 314, top 20%
Math46.0+9.4#74 of 327, top 23%

Weakest categories

CategoryScorevs medianRank
Multimodal31.6−6.9#104 of 128, top 82%
Agentic & Tool Use27.7−2.7#99 of 154, top 65%
Instruction Following72.1+0.9#140 of 305, top 46%

Closest competitors

The models ranked just above and below Grok 4.3. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Chatgpt 4o Latest 20250326#8243.8—21Compare
ERNIE 5.1#8343.8——Compare
GLM-5V-Turbo#8443.8$1.90—Compare
MiniMax-M3#8543.8$0.52—Compare
Qwen3 Max#8743.7$2.4048Compare
MiMo-V2-Omni#8843.6$0.18—Compare
Kimi K2.5 Instant#8943.6——Compare
Gemma 4 31B IT#9043.5$0.153Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
LMArena WebDev1357#87 of 113, top 77%LMArena2026-10-08
SciCode47.3%#51 of 121, top 43%highEpoch AI
WeirdML49.9%#48 of 119, top 41%Epoch AI
LMArena Coding1415#122 of 294, top 42%LMArena2026-10-08
ALE-Bench944.17#45 of 105, top 43%Epoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
GDP.pdf8%#35 of 36, top 98%Epoch AI
GDP.pdf8%highEpoch AI
LMArena Search1165#22 of 32, top 69%LMArena2026-08-24
Vending-Bench 235.26#55 of 60, top 92%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
NYT Connections (extended)55.2%#59 of 91, top 65%Lech Mazur benchmarks
CritPt0%Epoch AI
CritPt8%#53 of 134, top 40%highEpoch AI
CritPt0%noneEpoch AI
Chess Puzzles25%#44 of 129, top 35%highEpoch AI2026-06-17
LMArena Hard Prompts1396#131 of 297, top 45%LMArena2026-10-08
DTBench90.7%#36 of 151, top 24%highEpoch AI
LMCA38.3%#51 of 125, top 41%highEpoch AI
Epoch Capabilities Index149.16#59 of 213, top 28%Epoch AI2026-04-17
ForecastBench60.3#28 of 72, top 39%Epoch AI

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)42.8%#52 of 81, top 65%highEpoch AI2026-06-17
FrontierMath Tier 414.6%#49 of 63, top 78%highEpoch AI2026-06-17
OTIS Mock AIME 2024-202593.3%#42 of 173, top 25%highEpoch AI2026-06-17
ProofBench11%#62 of 77, top 81%highEpoch AI
LMArena Math1388#141 of 285, top 50%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond88.8%#45 of 186, top 25%highEpoch AI2026-06-17
SimpleQA Verified33.2%#54 of 77, top 71%highEpoch AI2026-08-27
LMArena Expert1385#135 of 273, top 50%LMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1229#67 of 122, top 55%LMArena2026-10-09
Blueprint-Bench 20%#31 of 31, top 100%Epoch AI

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1385#120 of 297, top 41%LMArena2026-10-08
LMArena Chinese1422#126 of 285, top 45%LMArena2026-10-08
LMArena French1412#109 of 223, top 49%LMArena2026-10-08
LMArena German1395#97 of 231, top 42%LMArena2026-10-08
LMArena Japanese1379#78 of 211, top 37%LMArena2026-10-08
LMArena Korean1356#100 of 213, top 47%LMArena2026-10-08
LMArena Russian1399#106 of 283, top 38%LMArena2026-10-08
LMArena Spanish1398#113 of 226, top 50%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1366#135 of 298, top 46%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1393#123 of 291, top 43%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1397#121 of 297, top 41%LMArena2026-10-08
LMArena Creative Writing1380#104 of 295, top 36%LMArena2026-10-08
EQ-Bench 41075#25 of 28, top 90%EQ-Bench
LMArena Multi-Turn1406#115 of 295, top 39%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
bedrock$1.25$2.50$0.202026-10-10
openrouter$1.25$2.50$0.202026-10-10
vertex$1.25$2.50$0.202026-10-10
xai$1.25$2.50$0.202026-10-10

All xAI API prices → Estimate your cost →

Compare Grok 4.3

Other xAI models

Frequently asked questions

How good is Grok 4.3?

Grok 4.3 by xAI ranks 86th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.8. Its strongest category is knowledge, where it ranks 62nd. API pricing starts at $1.25 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.

How much does Grok 4.3 cost?

Grok 4.3 costs $1.25 per million input tokens and $2.50 per million output tokens on xAI's own API, with cached input at $0.20.

What is Grok 4.3's context window?

Grok 4.3 accepts up to 1M tokens of input and can write up to 30K tokens in one response.

Is Grok 4.3 open source?

No. Grok 4.3 is proprietary and available only through xAI's API and partner platforms.

What are Grok 4.3's strengths and weaknesses?

Relative to other ranked models, Grok 4.3 places best in reasoning, knowledge, math and lowest in multimodal, agentic & tool use, instruction following.

What is Grok 4.3 best at?

Its best category is knowledge, where it ranks 62nd on Noometry.