Models / Grok 4.3

xAI

Grok 4.3

Grok 4.3 is strongest at reasoning and knowledge; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is DeepSeek-V4-Flash (0423), at $0.15 per million tokens against $1.56.

Superseded. Grok 4.20 is xAI's newer model in this line, at $1.56 blended: see Grok 4.20 or compare the two.

Results 16 Nov 2026 · 53 results · 6 sources

Test Grok 4.3 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.25 in · $2.50 out
xAI's list price, 10 Nov 2026 · compare prices$0.20 cached input · 20% off in batch
Speed
Not measured
Intelligence Index
24.9
Artificial Analysis, at high reasoning; 14.0–24.9 across 4 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
xAI, based in the US
Weights not published
Released
17 Apr 2026
1,000,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 75th of 185Claude Opus 5.5 – $1.56 blended, 63rd percentilecheapest: Mistral Nemo –
Models priced $1–3 per million tokens 21st of 34Muse Spark 1.3 – sets this group –
Models with similar intelligence sets this group – $1.56 blended, 62nd percentilecheapest: DeepSeek-V4-Flash (0423) –
Models from developers based in the US 45th of 92Claude Opus 5.5 – $1.56 blended, 44th percentilecheapest: Gemma 3 4B –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $1–3 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 117th of 159 available · 28th of 31 at its price
BenchmarkGrok 4.3Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 39.7% 70th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 12.4% 64th of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $35.26 48th of 53 GPT-6 Astra $15,515
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 49th of 51 available · 12th of 12 at its price
BenchmarkGrok 4.3Rank among availableBest available
GDP.pdfGDP.pdf: professional document tasks · reported 8.0% 31st of 31 GPT-5.6 Sol 30.7%
  • APEX-Agents: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 62nd of 187 available · 17th of 35 at its price
BenchmarkGrok 4.3Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 24.9 75th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 37.2% 55th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 90.1% 38th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 58th of 169 available · 15th of 28 at its price
BenchmarkGrok 4.3Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,441 62nd of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 57.7 37th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 107th of 139 available · 24th of 26 at its price
BenchmarkGrok 4.3Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,428 79th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 33.2% 51st of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Grok 4.3 at $1.56 blended, Intelligence Index 24.9. "Similar intelligence" means within 4 points or better.

Where to run it

2 hosts on OpenRouter at the standard service tier, with a median of $1.56 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
xAInot stated$1.25$2.50$1.56
xAInot stated$1.25$2.50$1.56

Other service tiers, not counted above: xAI priority $2.50 in, $5.00 out; xAI priority $2.50 in, $5.00 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Grok 4.3Muse Spark 1.3
most intelligent at $1–3 per million tokens
DeepSeek-V4-Flash (0423)
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $1.56 $2.00$0.15$8.00
Tokens a second – 254–96
Intelligence Index 24.9 48.124.457.6
Spring Prompt overall – 59–82
Rank among available models, by use case
Product listings – 17th–13th
Decks from an analysis – 25th–7th
User surveys – ––4th
Marketing planning – 25th–9th
Agents and tool use 117th of 159 13th59th3rd
Professional work 49th of 51 8th–3rd
Reasoning and knowledge 62nd of 187 11th69th1st
Writing 58th of 169 7th63rd5th
Sticking to the facts 107th of 139 11th81st3rd
Speed under pressure – 33rd––

Shaded figures are better than Grok 4.3's. A dash means no result.

Where it has been measured

21st most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the bottom quarter for professional work.

Artificial Analysis lists it but has not published a speed for it yet

Every result

53 published results from 6 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 8 results
MeasureValueRankConfigurationDated
Arena Search: overallArena rating, higher is better 1,193
1,188–1,199
17 of 34 Grok 4.3 (arena search) 24 Aug 2026
Arena Text factuality: overallArena rating, higher is better 1,428
1,425–1,431
120 of 182 Grok 4.3 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,439
1,433–1,445
104 of 406 Grok 4.3 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,422
1,416–1,429
80 of 411 Grok 4.3 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,452
1,444–1,460
111 of 363 Grok 4.3 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,414
1,409–1,420
122 of 413 Grok 4.3 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,441
1,438–1,445
94 of 413 Grok 4.3 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,424
1,418–1,430
87 of 412 Grok 4.3 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 38 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 42.2 118 of 187 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 35.2 129 of 187 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 24.9 156 of 413 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 24.3 163 of 413 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 24.8 158 of 413 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 14.0 266 of 413 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 90.1% 64 of 360 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 84.3% 132 of 360 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 89.0% 83 of 360 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 65.8% 276 of 360 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 37.2% 107 of 419 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 18.4% 215 of 419 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 30.0% 148 of 419 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 6.8% 317 of 419 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 81.3% 4 of 288 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 81.0% 6 of 288 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 83.3% 1 of 288 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 47.6% 152 of 288 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 73.0% 174 of 407 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 74.0% 163 of 407 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 75.0% 152 of 407 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 32.3% 333 of 407 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 48.3% 127 of 205 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 39.4% 167 of 205 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 39.7% 123 of 188 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 34.1% 131 of 188 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 37.9% 60 of 282 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 26.5% 121 of 282 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 30.3% 107 of 282 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 18.9% 150 of 282 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 12.4% 114 of 175 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 8.0% 137 of 175 Grok 4.3 (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 97.7% 7 of 286 Grok 4.3 (high reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 88.9% 60 of 286 Grok 4.3 (low reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 91.2% 52 of 286 Grok 4.3 (medium reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 65.8% 137 of 286 Grok 4.3 (no reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

GDP.pdf · reported by GDP.pdf · 2 results
MeasureValueRankConfigurationDated
GDP.pdf: professional document tasks% of rubric, higher is better 8.0% 46 of 49 Grok 4.3 6 Jun 2026
GDP.pdf: professional document tasks% of rubric, higher is better 8.0% 46 of 49 Grok 4.3 (high reasoning) 1 Oct 2026

Not shown: Not your documents; 100 tasks, so small differences are noise.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 33.2% 57 of 85 Grok 4.3 (high reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 21.0% 203 of 379 Grok 4.3 2 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.34 241 of 379 Grok 4.3 2 May 2026
UGI: writing scorescore out of 100, higher is better 57.7 117 of 379 Grok 4.3 2 May 2026

Not shown: Not other format limits such as character counts or bullet counts.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $35.26 58 of 63 Grok 4.3 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Will Grok 4.3 work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.