BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases8

Gemini 4 Carbon vs Grok 4.20

Full profiles: Gemini 4 Carbon (Google) and Grok 4.20 (SpaceXAI): every benchmark, price and rank.

Updated · Data from 8 sources

As of 29 Oct 2026, Gemini 4 Carbon is ahead of Grok 4.20 on quality (65.1 vs 58.5 on the BenchLeader Index), but Grok 4.20 is 5.1× cheaper at $1.56 vs $8.00 per 1M tokens blended. Gemini 4 Carbon leads in every category we measure both in.

Key facts (as of 29 Oct 2026)

  • Gemini 4 Carbon scores 65.1 on the BenchLeader Index and Grok 4.20 scores 58.5 (BenchLeader, 29 Oct 2026).
  • Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 29 Oct 2026).
  • Grok 4.20 costs $1.56 per 1M tokens blended (list price, 29 Oct 2026).
  • Of the 7 benchmarks both models have, Gemini 4 Carbon leads 7 (BenchLeader, 29 Oct 2026).
Gemini 4 Carbon benchmarks high Google Grok 4.20 benchmarks thinking SpaceXAIOpen in the comparison tool

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingGemini 4 Carbon72 vs 54 category score; Vibe Code Bench v1.1 89.1% vs 4.1%High
ReasoningGemini 4 Carbon79 vs 61 category score; Humanity's Last Exam (AA) 60.4% vs 34.5%High
KnowledgeGemini 4 Carbon76 vs 53 category scoreHigh
Long documentsGemini 4 Carbon65 vs 59 category score; AA-LCR v1.1 79.3% vs 69.0%Medium
Chat quality (human preference)–Only Grok 4.20 has an Arena rating (66 category score)Not comparable
Lowest costGrok 4.20$1.56 vs $8.00 per 1M blended; agentic coding session $0.085 vs $0.320–
Fastest first answerGrok 4.2016.6 s (Grok 4.20 (thinking)) vs 103.1 s (Gemini 4 Carbon (high)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Gemini 4 Carbon (high) leads on quality: 65.1 vs 58.5.
  • Gemini 4 Carbon (high) is stronger in coding, knowledge, long context, reasoning.
  • Grok 4.20 (thinking) is stronger in agents & tools, human preference, instruction following, maths, multimodal.
  • Grok 4.20 (thinking) is 5.1× cheaper ($1.56 vs $8.00 per 1M blended).

At a glance

SpecGemini 4 CarbonGrok 4.20
DeveloperGoogleSpaceXAI
Released28 Oct 202617 Feb 2026
Context window (tokens)1,000,0002,000,000
Compared atGemini 4 Carbon (high)Grok 4.20 (thinking)
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / –$1.25 / $2.50 / $0.200

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGemini 4 Carbon (high)Grok 4.20 (thinking)Leader
Reasoning78.961.1Gemini 4 Carbon
Coding71.753.6Gemini 4 Carbon
Agents & tools–50.5not comparable
Maths–54.0not comparable
Knowledge75.852.9Gemini 4 Carbon
Instruction following–78.6not comparable
Human preference–66.1not comparable
Multimodal–58.4not comparable
Long context64.559.1Gemini 4 Carbon

Where sources disagree

Across the 7 benchmarks both have, Gemini 4 Carbon leads 7, Grok 4.20 leads 0. Every overall index that rates both puts Gemini 4 Carbon ahead.

Overall indexGemini 4 Carbon (high)Grok 4.20 (thinking)Leader
BenchLeader Index65.158.5Gemini 4 Carbon

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

MeasureGemini 4 Carbon (high)Grok 4.20 (thinking)
Blended price per 1M tokens$8.00$1.56
Input / output per 1M$4.00 / $20.00$1.25 / $2.50
Cached input per 1M–$0.200
Price per task: chat reply$0.0076$0.0013
Price per task: summarize a 30-page report$0.060$0.017
Price per task: code edit$0.054$0.011
Price per task: agentic coding session$0.320$0.085
Price per task: structured extraction$0.012$0.0030
Cost to run a full benchmark suite$7.76–
Output speed100 tok/s104 tok/s
Time to first answer103.1 s16.6 s
Time to a complete answer108.1 s21.4 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Carbon (high) scores 65.1 and takes 103 s to its first answer token. Grok 4.20 (thinking) scores 58.5 and takes 17 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

90 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGemini 4 Carbon (high)Grok 4.20 (thinking)
BenchLeader IndexBenchLeader65.158.5
Coding scoreBenchLeader71.753.6
Knowledge scoreBenchLeader75.852.9
Long context scoreBenchLeader64.559.1
Reasoning scoreBenchLeader78.961.1
Agents & tools scoreBenchLeader–50.5
Human preference scoreBenchLeader–66.1
Instruction following scoreBenchLeader–78.6
Maths scoreBenchLeader–54.0
Multimodal scoreBenchLeader–58.4
Blended price $/MBenchLeader$8.00$1.56
Output speedBenchLeader100 tok/s104 tok/s
Time to first answerBenchLeader103.1 s16.6 s
Context windowBenchLeader1,000,000 tokens2,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–89.3%
Arena Hard PromptsArena (LMArena)–1489
GPQA Diamond (AA)Artificial Analysis–91.1%
Humanity's Last Exam (AA)Artificial Analysis60.4%34.5%
HLE-Diamond (AA)Artificial Analysis69.1%–
GPQA Diamond (Vals)Vals AI–88.6%
Kagi LLM BenchmarkKagi LLM Benchmark–75.0%
ARC-AGI-1ARC Prize–89.5%
ARC-AGI-2ARC Prize–65.1%
ARC-AGI-3ARC Prize–0.1%
CritPtArtificial Analysis36.0%6.6%
CritPt v2 hard subset (AA)Artificial Analysis63.0%–
Chess PuzzlesEpoch AI Benchmarking Hub–29.0%
CL-benchEpoch AI Benchmarking Hub–22.2%†
CL-bench LifeEpoch AI Benchmarking Hub–11.9%†
LMCAEpoch AI Benchmarking Hub–38.7%†
DTBenchEpoch AI Benchmarking Hub–90.1%†
ForecastBenchForecastBench–64.5%
Coding
SciCodeSciCode64.2%–
WeirdMLWeirdML–52.3%†
Arena CodingArena (LMArena)–1511
Arena WebDevArena (LMArena)–1375
LiveCodeBenchVals AI–84.3%
SWE-bench (Vals)Vals AI–72.2%
Code MigrationVals AI–0.3%
Show all 90 benchmarks
MetricPublisherGemini 4 Carbon (high)Grok 4.20 (thinking)
Coding
Vibe Code Bench v1.1Vals AI89.1%4.1%
ALE-BenchEpoch AI Benchmarking Hub–1150.3†
Terminal-Bench 4.0 (AA)Artificial Analysis65.2%–
FrontierCode 1.1 (AA)Artificial Analysis48.5%–
FrontierCode 2.0 (AA)Artificial Analysis40.6%–
Agents & tools
Terminal-BenchTerminal-Bench–57.3%†
Terminal-Bench HardArtificial Analysis–37.9%
τ²-Bench Telecom (AA)Artificial Analysis–93.0%
Terminal-Bench 2.1 (Vals)Vals AI–44.2%
HiL-BenchScale AI SEAL–20.0%†
APEX-Agents (AA)Artificial Analysis–14.2%
Finance Agent v2Vals AI–28.5%
Finance Agent v2.1Vals AI67.2%–
Harvey's Legal Agent Benchmark v1.1Vals AI17.5%–
Harvey's Legal Agent Benchmark v1Vals AI–0.0%
Legal Research BenchVals AI55.8%13.9%
Tax Agent BenchVals AI48.9%7.0%
Terminal-Bench 2.0 (Vals)Vals AI–40.5%
Terminal-Bench 4.0 (Vals)Vals AI63.1%–
Vending-Bench 2Andon Labs16484.2†4662.9†
AutomationBenchArtificial Analysis77.8%–
GDP.pdf (AA)Artificial Analysis28.4%–
AA-Briefcase v1.1Artificial Analysis1609–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis64.8%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–44.9%
FrontierMath Tier 4Epoch AI Benchmarking Hub–17.1%
OTIS Mock AIMEEpoch AI Benchmarking Hub–92.2%
ProofBenchVals AI–14.0%
AIME (Vals)Vals AI–96.5%
Arena MathsArena (LMArena)–1465
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–30.2%
AA-Omniscience v1.1Artificial Analysis53.5–
MMLU-ProVals AI–86.3%
LegalBenchVals AI–77.7%
CorpFinVals AI–63.7%
TaxEvalVals AI–74.1%
MedQAVals AI–94.5%
CaseLaw v2Vals AI–54.5%
Excel Modeling BenchmarkVals AI–11.7%
Excel Modeling Benchmark v1.1Vals AI76.5%–
MedCodeVals AI–32.2%
MedScribeVals AI–63.4%
AA-Omniscience v1.1: accuracyArtificial Analysis58.3%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis88.6%–
Global-MMLU-Lite (AA)Artificial Analysis–89.5%
Instruction following
IFBenchArtificial Analysis–81.2%
Arena Instruction FollowingArena (LMArena)–1447
Human preference
Arena TextArena (LMArena)–1472
Arena Creative WritingArena (LMArena)–1446
Arena Multi-turnArena (LMArena)–1479
Arena Longer QueriesArena (LMArena)–1466
Multimodal
Arena VisionArena (LMArena)–1262
MMMU-ProArtificial Analysis–74.6%
MMMU-Pro (Vals)Vals AI–83.5%
MortgageTaxVals AI–45.4%
Blueprint-Bench 2Epoch AI Benchmarking Hub58.6%†0.0%†
Long context
AA-LCR v1.1Artificial Analysis79.3%69.0%
Arena DocumentArena (LMArena)–1439
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–152.1†
AA Intelligence Index v5.0Artificial Analysis59.4–
AA Intelligence Index v4.3.2Artificial Analysis–25.7
AA Progress Index v1Artificial Analysis351.6281.9
Vals IndexVals AI70.4–
Vals Finance IndexVals AI66.3%–
Vals Multimodal IndexVals AI–39.1%

Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Grok 4.20 (thinking): BenchLeader Index 59.0 → 58.5.
  • Grok 4.20 (thinking): 1 new result (AA Progress Index v1).
  • Grok 4.20 (thinking): 1 new result (Global-MMLU-Lite (AA)).
  • Grok 4.20 (thinking): 1 new result (Harvey's Legal Agent Benchmark v1).
  • Grok 4.20 (thinking): 1 score revision.
  • Grok 4.20 (thinking): BenchLeader Index 59.5 → 59.0.
  • Grok 4.20 (thinking): input price moved from $2.00/M to $1.25/M (38% down); output price moved from $6.00/M to $2.50/M (58% down).
  • Grok 4.20 (thinking): 1 score revision.
  • Grok 4.20 (thinking): 1 score revision.
  • Grok 4.20 (thinking): BenchLeader Index 60.0 → 59.5.

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

Gemini 4 Carbon vs Grok 4.20: questions

Is Gemini 4 Carbon better than Grok 4.20?
Gemini 4 Carbon (high) leads on quality: 65.1 vs 58.5. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Carbon (high) is ahead overall as of 29 Oct 2026, but check the category scores for your use.
Gemini 4 Carbon vs Grok 4.20: which is cheaper, and will that change?
Grok 4.20 is cheaper today: $1.56 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemini 4 Carbon or Grok 4.20 better for coding?
Gemini 4 Carbon scores higher in coding (72 vs 54 on the category index, where 50 is average).
Which is faster, Gemini 4 Carbon or Grok 4.20?
Grok 4.20 streams faster (104 vs 100 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Gemini 4 Carbon scores higher on long-context benchmarks (65 vs 59). Grok 4.20 accepts more context: 2,000,000 against 1,000,000 tokens for Gemini 4 Carbon.
More questions (3)
Which has lower latency?
Grok 4.20 answers first: 16.6 s against 103.1 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Gemini 4 Carbon vs Grok 4.20?
Across the 7 benchmarks both have, Gemini 4 Carbon leads 7, Grok 4.20 leads 0. Every overall index that rates both puts Gemini 4 Carbon ahead.
When was Gemini 4 Carbon released?
Gemini 4 Carbon was released on 28 Oct 2026.