Models / Grok 4 (0709)

xAI

Grok 4 (0709)

Grok 4 (0709) is best for agents and tool use; it is not on sale through OpenRouter, so it is here for reference.

Superseded.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

Results 16 Nov 2026 · 26 results · 3 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
Not measured
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
xAI, based in the US
Weights not published
Released
Not recorded
no launch date in our tracker or our sources

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. 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 21st of 160 available
BenchmarkGrok 4 (0709)Rank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 63.0% 6th of 37 Claude Opus 4.5 77.5%
  • tau2-bench: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge Not measured
  • Artificial Analysis: has not measured this model.
WritingWhat people prefer in blind comparisons, and judged writing quality 61st of 170 available
BenchmarkGrok 4 (0709)Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,411 91st of 154 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 67.0 19th of 125 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 116th of 140 available
BenchmarkGrok 4 (0709)Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,418 86th of 110 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: has not measured this model.
  • SimpleQA Verified (Epoch AI): 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

  • XAI's newer model in this lineGrok 4.20$1.56 blended · Intelligence Index 25.7
  • The most capable open-weights modelMiMo-V2.6-Pro$0.54 blended · Intelligence Index 46.3

Against Grok 4 (0709). "Similar intelligence" means within 4 points or better.

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 (0709)Claude Fable 5.2
leads overall
Grok 4.7
xAI's best other model
Claude Opus 5.5
near the top overall
GPT-6.1 Sol
near the top overall
Price per million tokens – $16.00$3.00$8.00$4.00
Tokens a second – –749653
Intelligence Index – –46.457.651.8
Spring Prompt overall – 90408280
Rank among available models, by use case
Product listings – 5th9th13th2nd
Decks from an analysis – 4th12th7th5th
User surveys – 1st–4th3rd
Marketing planning – 1st24th9th–
Agents and tool use 21st of 160 –34th3rd6th
Professional work – ––3rd9th
Reasoning and knowledge – –23rd1st6th
Writing 61st of 170 –63rd5th16th
Sticking to the facts 116th of 140 –102nd3rd18th
Speed under pressure – 8th––3rd

Shaded figures are better than Grok 4 (0709)'s. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), in the top quarter (by percentile) for agents and tool use; in the bottom quarter for sticking to the facts.

Not timed: Artificial Analysis, our source for speed, has not tested it

Every result

26 published results from 3 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,418
1,412–1,424
134 of 182 Grok 4 (0709) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,395
1,388–1,403
166 of 406 Grok 4 (0709) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,395
1,386–1,403
115 of 411 Grok 4 (0709) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,431
1,418–1,444
142 of 363 Grok 4 (0709) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,397
1,390–1,403
150 of 413 Grok 4 (0709) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,411
1,407–1,415
147 of 413 Grok 4 (0709) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,398
1,392–1,405
127 of 412 Grok 4 (0709) 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 75.4% 70 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: irrelevance detection% correct, higher is better 84.3% 36 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: memory% correct, higher is better 55.9% 4 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 50.5% 11 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 33.9% 38 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 47.0% 19 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 61.4% 10 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 63.0% 9 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 87.5% 27 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 81.3% 41 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 85.4% 41 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 82.8% 61 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 75.6% 37 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 72.5% 52 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025
BFCL: web search% correct, higher is better 82.0% 4 of 109 Grok 4 (0709, bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 74.0% 13 of 109 Grok 4 (0709, bfcl prompt) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 17.0% 148 of 379 Grok 4 (0709) 24 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.36 157 of 379 Grok 4 (0709) 24 Sep 2025
UGI: writing scorescore out of 100, higher is better 67.0 49 of 379 Grok 4 (0709) 24 Sep 2025

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

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.