Share promptsSign inExplore benchmarks

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

On the 20 public leaderboards where both have a reported score, ChatGPT’s best-ranked model scores higher on 9, Gemini’s on 10, and 1 is tied. Counting only the 11 leaderboards their sources still update: ChatGPT 4, Gemini 6, 1 tied.

In plain words

  • Multi-domain agent tasks: Gemini higher on 1 of 1 (Vals Index).
  • Legal: ChatGPT higher on 1 of 4 (Legal Benchmarks: Data Extraction); Gemini higher on 2 of 4 (LegalBench and Legal Research Bench); tied on Legal Benchmarks: Contract Workflows.
  • Health & medical: ChatGPT higher on 2 of 3 (HealthBench (independent run) and MedQA); Gemini higher on 1 of 3 (MedCode).
  • Finance: ChatGPT higher on 1 of 2 (CorpFin v2); Gemini higher on 1 of 2 (Finance Agent).
  • Coding: ChatGPT higher on 1 of 2 (SWE-bench Verified); Gemini higher on 1 of 2 (LiveCodeBench).
  • Agents & tool use: ChatGPT higher on all 2 (Terminal-Bench 4.0 and Terminal-Bench 2.1).
  • Reasoning & knowledge: ChatGPT higher on 1 of 4 (Humanity's Last Exam); Gemini higher on 3 of 4 (GPQA Diamond, AIME and MMLU Pro).
  • Chat preference: Gemini higher on 1 of 1 (LMArena Text Arena).
  • Multilingual: ChatGPT higher on 1 of 1 (MGSM).
  • ChatGPT’s best-ranked entry is most often GPT-6 Astra (5 of 20); Gemini’s is most often Gemini 4 Argon (5 of 20).

ChatGPT here means OpenAI’s GPT and o-series models (the open-weight GPT OSS models are left out); 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

BenchmarkChatGPTGeminiHigher score
Vals IndexAccuracy · dated 21 Oct 202665.02%GPT-6 Astra · #569.24%Gemini 4 Argon · #3Gemini higherby 4.22 pts

Health & medical

BenchmarkChatGPTGeminiHigher score
HealthBench (independent run)HealthBench · checked 22 Oct 202658.5%GPT-6.1 Sol (max) · #349.1%Gemini 4 Argon (high) · #13ChatGPT higherby 9.4 pts
MedCodeAccuracy · dated 13 Oct 202652.73%GPT 5.1 · #1359.06%Gemini 3.1 Pro Preview (02/26) · #2Gemini higherby 6.33 pts
MedQAAccuracy · dated 16 Apr 2026 · no longer updated96.52%o1 · #196.37%Gemini 3.1 Pro Preview (02/26) · #3ChatGPT higherby 0.15 pts

Finance

BenchmarkChatGPTGeminiHigher score
Finance AgentAccuracy · dated 19 Oct 202661.82%GPT-6.1 Sol · #1367.66%Gemini 4 Argon · #2Gemini higherby 5.84 pts
CorpFin v2Accuracy · dated 12 Aug 2026 · no longer updated68.42%GPT 5.5 · #966.43%Gemini 3 Flash (12/25) · #20ChatGPT higherby 1.99 pts

Coding

BenchmarkChatGPTGeminiHigher score
SWE-bench VerifiedScore · dated 1 Sep 2026 · no longer updated96.2%GPT-5.6 Sol · #380.8%Gemini 3.7 Flash · #23ChatGPT higherby 15.4 pts
LiveCodeBenchAccuracy · dated 1 Sep 2026 · no longer updated87.99%GPT 5.2 Codex · #989.48%Gemini 3.8 Flash · #3Gemini higherby 1.49 pts

Agents & tool use

BenchmarkChatGPTGeminiHigher score
Terminal-Bench 4.0Score · dated 19 Oct 202659.60%GPT-6 Astra · #357.58%Gemini 4 Argon · #6ChatGPT higherby 2.02 pts
Terminal-Bench 2.1Score · dated 28 Sep 2026 · no longer updated87.27%GPT-6 Astra · #281.27%Gemini 3.8 Flash · #8ChatGPT higherby 6.00 pts

Reasoning & knowledge

BenchmarkChatGPTGeminiHigher score
Humanity's Last ExamAccuracy · checked 22 Oct 202654.80% ±1.94GPT 6 Astra · #146.44% ±1.96gemini-3.1-pro-preview (thinking high) · #3ChatGPT higherby 8.36 pts
GPQA DiamondAccuracy · dated 1 Sep 2026 · no longer updated95.20%GPT-5.6 Sol · #295.45%Gemini 3.1 Pro Preview (02/26) · #1Gemini higherby 0.25 pts
AIMEAccuracy · dated 16 Apr 2026 · no longer updated96.88%GPT 5.2 · #298.13%Gemini 3.1 Pro Preview (02/26) · #1Gemini higherby 1.25 pts
MMLU ProAccuracy · dated 1 Sep 2026 · no longer updated89.10%GPT-5.6 Sol · #1690.99%Gemini 3.1 Pro Preview (02/26) · #4Gemini higherby 1.89 pts

Chat preference

BenchmarkChatGPTGeminiHigher score
LMArena Text ArenaArena score · dated 20 Oct 20261484 ±4GPT-5.6 Sol (xHigh) · #211524 ±9Gemini 4 Argon (High) · #1 · preliminaryGemini higherby 40

Multilingual

BenchmarkChatGPTGeminiHigher score
MGSMAccuracy · dated 9 Jan 2026 · no longer updated94.00%GPT 5.2 · #693.93%Gemini 3 Pro (11/25) · #7ChatGPT higherby 0.07 pts

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

Test ChatGPT and Gemini on your own work

Run the same prompt in both and compare the answers. Prompts for ChatGPT → · 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 ChatGPT better than Gemini?

On the 20 public leaderboards where both have a reported score, ChatGPT’s best-ranked model scores higher on 9, Gemini’s on 10, and 1 is tied. Counting only the 11 leaderboards their sources still update: ChatGPT 4, Gemini 6, 1 tied. Which is better depends on the task: the leaders differ by benchmark, and scores from different tests are not directly comparable.

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

Vals Index: Gemini 69.24% vs ChatGPT 65.02%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is ChatGPT or Gemini better for legal work?

Legal Benchmarks: Contract Workflows: tied at 25.8%; Legal Benchmarks: Data Extraction: ChatGPT 56.7% vs Gemini 53.3%; LegalBench: Gemini 88.30% vs ChatGPT 86.97%; Legal Research Bench: Gemini 54.81% vs ChatGPT 48.08%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is ChatGPT or Gemini better for health & medical questions?

HealthBench (independent run): ChatGPT 58.5% vs Gemini 49.1%; MedCode: Gemini 59.06% vs ChatGPT 52.73%; MedQA: ChatGPT 96.52% vs Gemini 96.37%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is ChatGPT or Gemini better for finance?

Finance Agent: Gemini 67.66% vs ChatGPT 61.82%; CorpFin v2: ChatGPT 68.42% vs Gemini 66.43%. Each figure is the best-ranked model from each side on that leaderboard, as published by its source.

Is ChatGPT or Gemini better for coding?

SWE-bench Verified: ChatGPT 96.2% vs Gemini 80.8%; LiveCodeBench: Gemini 89.48% vs ChatGPT 87.99%. 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, MMLU Pro and MGSM 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 ChatGPT model and the best-ranked Gemini model, so the model can change from one benchmark to the next. ChatGPT’s top entry is most often GPT-6 Astra (5 of 20); Gemini’s is most often Gemini 4 Argon (5 of 20). ChatGPT here means OpenAI’s GPT and o-series models (the open-weight GPT OSS models are left out); Gemini means Google’s Gemini models.