Share promptsSign inExplore benchmarks

Grok vs Gemini: AI benchmark scores compared (Oct 2026)

On the 18 public leaderboards where both have a reported score, Grok’s best-ranked model scores higher on 3, Gemini’s on 13, and 2 are tied. Counting only the 10 leaderboards their sources still update: Grok 1, Gemini 7, 2 tied.

In plain words

  • Multi-domain agent tasks: Gemini higher on 1 of 1 (Vals Index).
  • Legal: Gemini higher on 2 of 4 (LegalBench and Legal Research Bench); tied on Legal Benchmarks: Contract Workflows and Legal Benchmarks: Data Extraction.
  • Health & medical: Grok higher on 1 of 3 (HealthBench (independent run)); Gemini higher on 2 of 3 (MedCode and MedQA).
  • Finance: Grok higher on 1 of 2 (CorpFin v2); Gemini higher on 1 of 2 (Finance Agent).
  • Coding: Grok higher on 1 of 2 (SWE-bench Verified); Gemini higher on 1 of 2 (LiveCodeBench).
  • Agents & tool use: Gemini higher on all 2 (Terminal-Bench 4.0 and Terminal-Bench 2.1).
  • Reasoning & knowledge: Gemini higher on all 3 (GPQA Diamond, AIME and MMLU Pro).
  • Chat preference: Gemini higher on 1 of 1 (LMArena Text Arena).
  • Grok’s best-ranked entry is most often Grok 4.6 (9 of 18); Gemini’s is most often Gemini 4 Argon (5 of 18).

Grok here means xAI’s Grok models; Gemini means Google’s Gemini models. On each leaderboard we compare each side’s best-ranked model, so the model can differ by benchmark. A side only counts where it appears on the leaderboard (we keep each source’s top rows).

Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results

Multi-domain agent tasks

BenchmarkGrokGeminiHigher score
Vals IndexAccuracy · dated 21 Oct 202658.56%Grok 4.7 · #1169.24%Gemini 4 Argon · #3Gemini higherby 10.68 pts

Health & medical

BenchmarkGrokGeminiHigher score
HealthBench (independent run)HealthBench · checked 22 Oct 202656.0%Grok 4.7 (xhigh) · #849.1%Gemini 4 Argon (high) · #13Grok higherby 6.9 pts
MedCodeAccuracy · dated 13 Oct 202649.55%Grok 4.7 · #2259.06%Gemini 3.1 Pro Preview (02/26) · #2Gemini higherby 9.51 pts
MedQAAccuracy · dated 16 Apr 2026 · no longer updated94.55%Grok 4.20 (Reasoning) · #1696.37%Gemini 3.1 Pro Preview (02/26) · #3Gemini higherby 1.82 pts

Finance

BenchmarkGrokGeminiHigher score
Finance AgentAccuracy · dated 19 Oct 202660.59%Grok 4.7 · #1867.66%Gemini 4 Argon · #2Gemini higherby 7.07 pts
CorpFin v2Accuracy · dated 12 Aug 2026 · no longer updated68.53%Grok 4.3 · #866.43%Gemini 3 Flash (12/25) · #20Grok higherby 2.10 pts

Coding

BenchmarkGrokGeminiHigher score
SWE-bench VerifiedScore · dated 1 Sep 2026 · no longer updated95.6%Grok 4.6 · #480.8%Gemini 3.7 Flash · #23Grok higherby 14.8 pts
LiveCodeBenchAccuracy · dated 1 Sep 2026 · no longer updated88.22%Grok 4.6 · #789.48%Gemini 3.8 Flash · #3Gemini higherby 1.26 pts

Agents & tool use

BenchmarkGrokGeminiHigher score
Terminal-Bench 4.0Score · dated 19 Oct 202628.79%Grok 4.7 · #2057.58%Gemini 4 Argon · #6Gemini higherby 28.79 pts
Terminal-Bench 2.1Score · dated 28 Sep 2026 · no longer updated78.28%Grok 4.6 · #1381.27%Gemini 3.8 Flash · #8Gemini higherby 2.99 pts

Reasoning & knowledge

BenchmarkGrokGeminiHigher score
GPQA DiamondAccuracy · dated 1 Sep 2026 · no longer updated94.70%Grok 4.6 · #395.45%Gemini 3.1 Pro Preview (02/26) · #1Gemini higherby 0.75 pts
AIMEAccuracy · dated 16 Apr 2026 · no longer updated96.46%Grok 4.20 (Reasoning) · #698.13%Gemini 3.1 Pro Preview (02/26) · #1Gemini higherby 1.67 pts
MMLU ProAccuracy · dated 1 Sep 2026 · no longer updated89.40%Grok 4.6 · #1190.99%Gemini 3.1 Pro Preview (02/26) · #4Gemini higherby 1.59 pts

Chat preference

BenchmarkGrokGeminiHigher score
LMArena Text ArenaArena score · dated 20 Oct 20261475 ±5Grok 4.20 Beta 1 · #391524 ±9Gemini 4 Argon (High) · #1 · preliminaryGemini higherby 49

Every score links to the leaderboard that published it. Sources: Vals AI ↗ · Legal Benchmarks ↗ · Artificial Analysis ↗ · LMArena ↗. ChatJudge does not run these tests.

Test Grok and Gemini on your own work

Run the same prompt in both and compare the answers. Prompts for Grok → · Prompts for Gemini →

ReviewsClaudeCompare two documents clause by clauseChecking a filled-in contract or proposal against its template.View prompt ProposalsChatGPTClarify commercial termsPricing, commission or partnership fees are being misread.View prompt
ResearchAny modelTurn messy text into a tableYou extract structured data from messy text. I will give you text and the fields I want. Return…View prompt AI Native SolutionsAI Native Solutions @ainativesolReport or remove
MarketingClaudeCustomer interviews to evidence-backed landing-page outlineFirst, extract exact quotes about desired outcomes, buying objections, and evidence customers ask…View prompt Nastation | AI for Client Work @NastaitonReport or remove
ResearchGeminiInvestor/stock due-diligenceAct as a forensic equity analyst. Conduct a deep research analysis for [COMPANY / TICKER] based on…View prompt MasterYoda @MasterYoda1991Report or remove
PricingClaudeUnit economics checkTesting whether your pricing survives your real usage costs.View prompt

Questions people ask

Is Grok better than Gemini?

On the 18 public leaderboards where both have a reported score, Grok’s best-ranked model scores higher on 3, Gemini’s on 13, and 2 are tied. Counting only the 10 leaderboards their sources still update: Grok 1, Gemini 7, 2 tied. Which is better depends on the task: the leaders differ by benchmark, and scores from different tests are not directly comparable.

Is Grok or Gemini better for multi-domain agent tasks?

Vals Index: Gemini 69.24% vs Grok 58.56%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is Grok or Gemini better for legal work?

Legal Benchmarks: Contract Workflows: tied at 25.8%; Legal Benchmarks: Data Extraction: tied at 53.3%; LegalBench: Gemini 88.30% vs Grok 86.31%; Legal Research Bench: Gemini 54.81% vs Grok 48.08%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is Grok or Gemini better for health & medical questions?

HealthBench (independent run): Grok 56.0% vs Gemini 49.1%; MedCode: Gemini 59.06% vs Grok 49.55%; MedQA: Gemini 96.37% vs Grok 94.55%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is Grok or Gemini better for finance?

Finance Agent: Gemini 67.66% vs Grok 60.59%; CorpFin v2: Grok 68.53% vs Gemini 66.43%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is Grok or Gemini better for coding?

SWE-bench Verified: Grok 95.6% vs Gemini 80.8%; LiveCodeBench: Gemini 89.48% vs Grok 88.22%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

How recent is this comparison?

It is rebuilt from our benchmark data, last checked on 22 Oct 2026. Each leaderboard’s own date is shown in the table. MedQA, CorpFin v2, SWE-bench Verified, LiveCodeBench, Terminal-Bench 2.1, GPQA Diamond, AIME and MMLU Pro are no longer updated by the source, so newer models may be missing there.

Which models are being compared?

On each leaderboard we take the best-ranked Grok model and the best-ranked Gemini model, so the model can change from one benchmark to the next. Grok’s top entry is most often Grok 4.6 (9 of 18); Gemini’s is most often Gemini 4 Argon (5 of 18). Grok here means xAI’s Grok models; Gemini means Google’s Gemini models.