BenchLeader
Menu

Gemini 4 Hydrogen vs Kimi K3.1 Pro

Full profiles: Gemini 4 Hydrogen (Google) and Kimi K3.1 Pro (Moonshot AI): every benchmark, price and rank.

Updated · Data from 8 sources

As of 13 Nov 2026, Gemini 4 Hydrogen and Kimi K3.1 Pro are neck and neck on quality (63.4 vs 61.3 on the BenchLeader Index, inside the ±3.4 margin), and Gemini 4 Hydrogen is 1.3× cheaper at $3.00 vs $4.00 per 1M tokens blended. Gemini 4 Hydrogen leads in every category we measure both in. Gemini 4 Hydrogen streams 3×+ faster.

Key facts (as of 13 Nov 2026)

  • Gemini 4 Hydrogen scores 63.4 on the BenchLeader Index and Kimi K3.1 Pro scores 61.3 (BenchLeader, 13 Nov 2026).
  • Gemini 4 Hydrogen costs $3.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Kimi K3.1 Pro costs $4.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Gemini 4 Hydrogen streams 3×+ faster than Kimi K3.1 Pro (Artificial Analysis, 7-day median, 13 Nov 2026).
  • Of the 8 benchmarks both models have, Gemini 4 Hydrogen leads 6 (BenchLeader, 13 Nov 2026).
  • On Arena WebDev, Gemini 4 Hydrogen is rated 1704 and Kimi K3.1 Pro 1687 (LMArena, as published by 13 Nov 2026).
Gemini 4 Hydrogen benchmarks high Google Kimi K3.1 Pro benchmarks max Moonshot AIAdd a third model

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
CodingEither69 vs 68 category score; Arena WebDev 1704 vs 1687Either
Agents & tool useEither62 vs 62 category score; Terminal-Bench 56.4% vs 59.7%Either
ReasoningGemini 4 Hydrogen70 vs 67 category score; Arena Hard Prompts 1514 vs 1504Medium
Chat quality (human preference)Either68 vs 68 on Arena votesEither
Lowest costGemini 4 Hydrogen$3.00 vs $4.00 per 1M blended; agentic coding session $0.120 vs $0.160–
Fastest first answerGemini 4 Hydrogen16.4 s (Gemini 4 Hydrogen (high)) vs 170.3 s (Kimi K3.1 Pro (max)) 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 Hydrogen (high) and Kimi K3.1 Pro (max) are neck and neck on quality (63.4 vs 61.3, within the ±3.4 margin).
  • Gemini 4 Hydrogen (high) is stronger in coding, human preference, reasoning.
  • Kimi K3.1 Pro (max) is stronger in agents & tools.
  • Gemini 4 Hydrogen (high) is 1.3× cheaper ($3.00 vs $4.00 per 1M blended).
  • Gemini 4 Hydrogen (high) streams 5.8× faster (180 vs 31 tokens per second).

At a glance

SpecGemini 4 HydrogenKimi K3.1 Pro
DeveloperGoogleMoonshot AI
Released12 Nov 202623 Oct 2026
Context window (tokens)1,048,5761,048,576
Compared atGemini 4 Hydrogen (high)Kimi K3.1 Pro (max)
Open weightsNoYes
Price in / out / cached input per 1M$1.50 / $7.50 / $0.075$2.00 / $10.00 / $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 Hydrogen (high)Kimi K3.1 Pro (max)Leader
Reasoning69.666.9Gemini 4 Hydrogen
Coding68.868.3level
Agents & tools61.962.0level
Maths67.8–not comparable
Knowledge68.5–not comparable
Human preference68.267.6level

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsHumanpreferenceGemini 4 Hydrogen, Reasoning: 69.6Gemini 4 Hydrogen, Coding: 68.8Gemini 4 Hydrogen, Agents & tools: 61.9Gemini 4 Hydrogen, Human preference: 68.2Kimi K3.1 Pro, Reasoning: 66.9Kimi K3.1 Pro, Coding: 68.3Kimi K3.1 Pro, Agents & tools: 62.0Kimi K3.1 Pro, Human preference: 67.6

Not drawn, measured for fewer than two of these models: Maths, Knowledge, Instruction following, Long context, Multimodal.

Model, click to add or removeIndex

Where sources disagree

Across the 8 benchmarks both have, Gemini 4 Hydrogen leads 6, Kimi K3.1 Pro leads 2. Every overall index that rates both puts Gemini 4 Hydrogen ahead.

Overall indexGemini 4 Hydrogen (high)Kimi K3.1 Pro (max)Leader
BenchLeader Index63.461.3neck and neck
AA Intelligence Index v5.050.846.5†Gemini 4 Hydrogen
Vals Index68.5†62.5Gemini 4 Hydrogen
Arena Text14901485Gemini 4 Hydrogen

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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGemini 4 Hydrogen (high)Kimi K3.1 Pro (max)
Blended price per 1M tokens$3.00$4.00
Input / output per 1M$1.50 / $7.50$2.00 / $10.00
Cached input per 1M$0.075$0.200
Price per task: chat reply$0.0029$0.0038
Price per task: summarize a 30-page report$0.022$0.030
Price per task: code edit$0.020$0.027
Price per task: agentic coding session$0.120$0.160
Price per task: structured extraction$0.0045$0.0060
Agentic coding session, input mostly cached$0.056$0.079
Cost per benchmark task (AA Index)$1.87$3.68
Output tokens per task (AA Index)85k–
Of which reasoning48k–
Time per task (AA Index)8 min–
Output speed180 tok/s31 tok/s
Time to first answer16.4 s170.3 s
Time to a complete answer63.3 s417.5 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $1.87 on Gemini 4 Hydrogen (high) and $3.68 on Kimi K3.1 Pro (max), and Kimi K3.1 Pro (max) used about 1.5× as many tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Hydrogen (high) scores 63.4 and takes 16 s to its first answer token. Kimi K3.1 Pro (max) scores 61.3 and takes 170 s to its first answer token; Kimi K3.1 Pro scores 60.9 in 170 s. 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

80 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 Hydrogen (high)Kimi K3.1 Pro (max)
BenchLeader IndexBenchLeader63.461.3
Agents & tools scoreBenchLeader61.962.0
Coding scoreBenchLeader68.868.3
Human preference scoreBenchLeader68.267.6
Knowledge scoreBenchLeader68.5–
Maths scoreBenchLeader67.8–
Reasoning scoreBenchLeader69.666.9
Blended price $/MBenchLeader$3.00$4.00
Output speedBenchLeader180 tok/s31 tok/s
Time to first answerBenchLeader16.4 s170.3 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
Arena Hard PromptsArena (LMArena)15141504
LiveBench 2.0 ReasoningLiveBench88.6%†91.1%†
Humanity's Last Exam (AA)Artificial Analysis–52.5%†
HLE-Diamond (AA)Artificial Analysis54.9%37.3%†
CritPtArtificial Analysis–24.6%†
CritPt v2 hard subset (AA)Artificial Analysis61.5%49.5%†
MysteryMechanismVals AI–26.1%
LMCAEpoch AI Benchmarking Hub–57.6%
DTBenchEpoch AI Benchmarking Hub–93.3%
Coding
SciCodeSciCode–60.8%†
Arena CodingArena (LMArena)15181530
Arena WebDevArena (LMArena)17041687
LiveBench 2.0 CodingLiveBench78.5%†67.8%†
IOIVals AI–81.9%
Vibe Code Bench v1.1Vals AI87.8%†84.9%
ALE-BenchEpoch AI Benchmarking Hub–1932.8
Terminal-Bench 4.0 (AA)Artificial Analysis54.0%67.2%†
Startrise FrontendStartrise–82.5%†
GameBench 2 OverallDuelLab GameBench 2–78.3†
GameBench 2 by reasoning settingDuelLab GameBench 2–84.0
Design Arena WebsiteDesign Arena1316†1321†
FrontierCode 1.1 (AA)Artificial Analysis–47.1%†
FrontierCode 2.0 (AA)Artificial Analysis36.3%25.4%†
Agents & tools
Terminal-BenchTerminal-Bench56.4%59.7%
APEX-AgentsMercor–65.5%†
Show all 80 benchmarks
MetricPublisherGemini 4 Hydrogen (high)Kimi K3.1 Pro (max)
Agents & tools
Arena AgentArena (LMArena)–4.9
LiveBench Long AgenticLiveBench61.8%†38.7%†
LiveBench BrowserLiveBench77.1%†75.9%†
HiL-BenchScale AI SEAL–61.3%†
GDPval-AA v2.1, normalised scoreArtificial Analysis–67.3%†
GDPval-AA v2.1Artificial Analysis–1861†
Analyst Agent (AA)Artificial Analysis–38.8%†
Finance Agent v2.1Vals AI65.1%†61.5%
Harvey's Legal Agent Benchmark v1.1Vals AI11.3%†11.7%
Legal Research BenchVals AI53.9%†37.5%
SREBenchVals AI–27.1%
Tax Agent BenchVals AI52.3%†24.9%
Terminal-Bench 4.0 (Vals)Vals AI54.0%†63.6%
Terminal-Bench ScienceVals AI–31.4%
AutomationBenchArtificial Analysis74.4%73.3%†
GDP.pdf (AA)Artificial Analysis30.0%31.4%†
AA-Briefcase v1.1Artificial Analysis14971675†
Design Arena AgenticDesign Arena–1288†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis41.4%34.3%†
CWE-Bench (AA)Artificial Analysis–60.8%†
DeepSec-Bench (AA)Artificial Analysis–36.7%†
CyberGym end-to-end (AA)Artificial Analysis–94.7%†
Maths
ProofBenchVals AI–91.0%†
Arena MathsArena (LMArena)1495–
Knowledge
LiveBench 2.0 Data AnalysisLiveBench83.2%†79.1%†
LiveBench ResearchLiveBench86.8%†82.1%†
AA-Omniscience v1.1Artificial Analysis43.729.9†
PRBench FinanceScale AI SEAL–47.5%†
PRBench LegalScale AI SEAL–47.9%†
BioMysteryBenchVals AI–75.6%
Excel Modeling Benchmark v1.1Vals AI75.8%†70.0%
DrugDiscoveryBenchScale AI SEAL–63.4%†
AA-Omniscience v1.1: accuracyArtificial Analysis48.2%48.9%†
AA-Omniscience v1.1: non-hallucinationArtificial Analysis91.3%62.7%†
Instruction following
Arena Instruction FollowingArena (LMArena)15031487
Human preference
Arena TextArena (LMArena)14901485
Arena Creative WritingArena (LMArena)14921453
Arena Multi-turnArena (LMArena)14761475
Arena Longer QueriesArena (LMArena)15141491
Multimodal
LiveBench DesignLiveBench77.3%†73.7%†
MMMU-ProArtificial Analysis–83.9%†
AA-3DArtificial Analysis–1112†
Long context
AA-LCR v1.1Artificial Analysis–86.3%†
MLCRArtificial Analysis21.1%†38.3%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–161.4†
LiveBench 2.0LiveBench77.0%†68.7%†
AA Intelligence Index v5.0Artificial Analysis50.846.5†
AA Intelligence Index v4.3.2Artificial Analysis–55.1†
AA Progress Index v1Artificial Analysis–340.7†
Vals IndexVals AI68.5†62.5
Vals Finance IndexVals AI66.1%†56.0%
Vals Science IndexVals AI–44.4%
AA Cyber IndexArtificial Analysis–64.1†
Safety & honesty
FORTRESSScale AI SEAL–18.6%†
Metadata
AA Openness IndexArtificial Analysis–33.3†

Data as of 2026-11-13. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Kimi K3.1 Pro (max): BenchLeader Index 60.4 → 61.3.
  • Gemini 4 Hydrogen (high): 10 new results (Arena Text, Arena Hard Prompts, Arena Coding…).
  • Kimi K3.1 Pro (max): 1 new result (Terminal-Bench).
  • Kimi K3.1 Pro (max): 9 new results (LMCA, DTBench, Arena Text…).
  • Kimi K3.1 Pro (max): 1 score revision.
  • Kimi K3.1 Pro (max): 1 score revision.
  • Kimi K3.1 Pro (max): 1 new result (SREBench); 1 score revision.
  • Kimi K3.1 Pro (max): 1 score revision.
  • Kimi K3.1 Pro (max): 1 new result (Arena Agent).
  • Kimi K3.1 Pro (max): 1 new result (ALE-Bench).

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

Gemini 4 Hydrogen vs Kimi K3.1 Pro: questions

Is Gemini 4 Hydrogen better than Kimi K3.1 Pro?
Gemini 4 Hydrogen (high) and Kimi K3.1 Pro (max) are neck and neck on quality (63.4 vs 61.3, within the ±3.4 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 13 Nov 2026, so check the category scores for your use.
Gemini 4 Hydrogen vs Kimi K3.1 Pro: which is cheaper, and will that change?
Gemini 4 Hydrogen is cheaper today: $3.00 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemini 4 Hydrogen or Kimi K3.1 Pro better for coding?
They are level in coding (69 vs 68 on the category index). On Arena WebDev, the top shared coding benchmark, it is 1704 for Gemini 4 Hydrogen against 1687 for Kimi K3.1 Pro.
Which is faster, Gemini 4 Hydrogen or Kimi K3.1 Pro?
Gemini 4 Hydrogen streams 3×+ faster (180 vs 31 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 4 Hydrogen or Kimi K3.1 Pro better for agents and tool use?
They are level in agentic tasks (62 vs 62 on the category index). On Terminal-Bench, the top shared agents & tools benchmark, it is 56.4% for Gemini 4 Hydrogen against 59.7% for Kimi K3.1 Pro.
More questions (4)
Which is better for long documents?
Both accept 1,048,576 tokens of context.
Which has lower latency?
Gemini 4 Hydrogen answers first: 16.4 s against 170.3 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 Hydrogen vs Kimi K3.1 Pro?
Across the 8 benchmarks both have, Gemini 4 Hydrogen leads 6, Kimi K3.1 Pro leads 2. Every overall index that rates both puts Gemini 4 Hydrogen ahead.
When was Gemini 4 Hydrogen released?
Gemini 4 Hydrogen was released on 12 Nov 2026.