BenchLeader

GPT-6.1 Terra vs Kimi K2.6

Full profiles: GPT-6.1 Terra (OpenAI) and Kimi K2.6 (Moonshot AI): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, GPT-6.1 Terra and Kimi K2.6 are neck and neck on quality (64.1 vs 59.3 on the BenchLeader Index, inside the ±7.4 margin), and Kimi K2.6 is 1.2× cheaper at $1.71 vs $2.00 per 1M tokens blended. GPT-6.1 Terra leads in every category we measure both in. GPT-6.1 Terra streams ~2× faster.

Key facts (as of 16 Nov 2026)

  • GPT-6.1 Terra scores 64.1 on the BenchLeader Index and Kimi K2.6 scores 59.3 (BenchLeader, 16 Nov 2026).
  • GPT-6.1 Terra costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Kimi K2.6 costs $1.71 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-6.1 Terra streams ~2× faster than Kimi K2.6 (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 12 benchmarks both models have, GPT-6.1 Terra leads 12 (BenchLeader, 16 Nov 2026).

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
Agents & tool useGPT-6.1 Terra63 vs 58 category score; GDPval-AA v2.1 1476 vs 1046Medium
Long documentsEither66 vs 65 category score; AA-LCR v1.1 82.7% vs 81.0%Either
Images and other mediaGPT-6.1 Terra67 vs 62 category score; MMMU-Pro 84.7% vs 79.4%Medium
Lowest costKimi K2.6$1.71 vs $2.00 per 1M blended; agentic coding session $0.073 vs $0.080–
Fastest first answerKimi K2.693.1 s (Kimi K2.6 (thinking)) vs 150.9 s (GPT-6.1 Terra (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

  • GPT-6.1 Terra (max) and Kimi K2.6 (thinking) are neck and neck on quality (64.1 vs 59.3, within the ±7.4 margin).
  • GPT-6.1 Terra (max) is stronger in agents & tools, long context, multimodal.
  • Kimi K2.6 (thinking) is 1.2× cheaper ($1.71 vs $2.00 per 1M blended).
  • GPT-6.1 Terra (max) streams 1.8× faster (72 vs 41 tokens per second).

At a glance

SpecGPT-6.1 TerraKimi K2.6
DeveloperOpenAIMoonshot AI
Released26 Oct 202620 Apr 2026
Context window (tokens)1,050,000262,144
Compared atGPT-6.1 Terra (max)Kimi K2.6 (thinking)
Open weightsNoYes
Price in / out / cached input per 1M$1.00 / $5.00 / $0.050$0.950 / $4.00 / $0.160

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.

CategoryGPT-6.1 Terra (max)Kimi K2.6 (thinking)Leader
Reasoning68.4–not comparable
Coding69.3–not comparable
Agents & tools63.458.4GPT-6.1 Terra
Maths71.7–not comparable
Knowledge61.4–not comparable
Instruction following–74.1not comparable
Multimodal67.261.7GPT-6.1 Terra
Long context66.065.2level
Composite65.0–not comparable

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 avg75Agents & toolsLong contextMultimodalGPT-6.1 Terra, Agents & tools: 63.4GPT-6.1 Terra, Long context: 66.0GPT-6.1 Terra, Multimodal: 67.2Kimi K2.6, Agents & tools: 58.4Kimi K2.6, Long context: 65.2Kimi K2.6, Multimodal: 61.7

Not drawn, measured for fewer than two of these models: Reasoning, Coding, Maths, Knowledge, Instruction following, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 12 benchmarks both have, GPT-6.1 Terra leads 12, Kimi K2.6 leads 0.

Overall indexGPT-6.1 Terra (max)Kimi K2.6 (thinking)Leader
BenchLeader Index64.159.3neck and neck

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.

MeasureGPT-6.1 Terra (max)Kimi K2.6 (thinking)
Blended price per 1M tokens$2.00$1.71
Input / output per 1M$1.00 / $5.00$0.950 / $4.00
Cached input per 1M$0.050$0.160
Price per task: chat reply$0.0019$0.0016
Price per task: summarize a 30-page report$0.015$0.014
Price per task: code edit$0.013$0.012
Price per task: agentic coding session$0.080$0.073
Price per task: structured extraction$0.0030$0.0027
Agentic coding session, input mostly cached$0.037$0.037
Cost per benchmark task (AA Index)$0.961–
Output tokens per task (AA Index)60k–
Of which reasoning39k–
Time per task (AA Index)14 min–
Output speed72 tok/s41 tok/s
Time to first answer150.9 s93.1 s
Time to a complete answer, last measured 13 Nov 2026375.7 s215.8 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Terra (max) scores 64.1 and takes 151 s to its first answer token; GPT-6.1 Terra (xhigh) scores 60.0 in 30 s, GPT-6.1 Terra (high) scores 59.6 in 10 s. Kimi K2.6 (thinking) scores 59.3 and takes 93 s to its first answer token; Kimi K2.6 scores 55.1 in 1 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

148 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.

MetricPublisherGPT-6.1 Terra (max)Kimi K2.6 (thinking)
BenchLeader IndexBenchLeader64.159.3
Agents & tools scoreBenchLeader63.458.4
Coding scoreBenchLeader69.3–
Composite scoreBenchLeader65.0–
Knowledge scoreBenchLeader61.4–
Long context scoreBenchLeader66.065.2
Maths scoreBenchLeader71.7–
Multimodal scoreBenchLeader67.261.7
Reasoning scoreBenchLeader68.4–
Instruction following scoreBenchLeader–74.1
Blended price $/MBenchLeader$2.00$1.71
Output speedBenchLeader72 tok/s41 tok/s
Time to first answerBenchLeader150.9 s93.1 s
Context windowBenchLeader1,050,000 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.3%90.8%†
SimpleBenchSimpleBench72.2%†–
Arena Hard PromptsArena (LMArena)–1485†
LiveBench 2.0 ReasoningLiveBench88.7%–
LiveBench 1.0 ReasoningLiveBench–79.4%
GPQA Diamond (AA)Artificial Analysis–91.1%
Humanity's Last Exam (AA)Artificial Analysis46.3%37.5%
HLE-Diamond (AA)Artificial Analysis47.3%–
GPQA Diamond (Vals)Vals AI–89.1%†
CritPtArtificial Analysis28.0%8.0%
CritPt v2 hard subset (AA)Artificial Analysis68.0%–
HLE-Diamond (Scale)Scale AI SEAL35.7%†–
Arena ExpertArena (LMArena)–1503†
Chess PuzzlesEpoch AI Benchmarking Hub–20.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub74.0%18.0%†
LMCAEpoch AI Benchmarking Hub–37.3%†
DTBenchEpoch AI Benchmarking Hub–90.9%†
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–76.7%†
SciCodeSciCode55.1%53.5%†
WeirdMLWeirdML–55.9%†
Arena CodingArena (LMArena)–1516†
Arena WebDevArena (LMArena)16781509†
LiveBench 2.0 CodingLiveBench89.2%–
LiveBench 1.0 CodingLiveBench–78.6%
SciCode (AA)Artificial Analysis55.1%51.5%
Show all 148 benchmarks
MetricPublisherGPT-6.1 Terra (max)Kimi K2.6 (thinking)
Coding
LiveCodeBenchVals AI–86.8%†
SWE-bench (Vals)Vals AI–76.2%†
Code MigrationVals AI–27.8%†
ProgramBenchVals AI–0.0%†
Vibe Code Bench v1.1Vals AI84.0%37.9%†
SWE Atlas v1.1Scale AI SEAL57.7%†–
SWE Atlas v1.1: Codebase QnAScale AI SEAL54.0%†–
SWE Atlas v1.1: Test WritingScale AI SEAL63.3%†–
SWE Atlas v1.1: RefactoringScale AI SEAL55.7%†–
MirrorCodeEpoch AI Benchmarking Hub76.7%–
ALE-BenchEpoch AI Benchmarking Hub2608.81092.7†
WeirdML v3WeirdML28.1%†–
Terminal-Bench 4.0 (AA)Artificial Analysis55.6%0.5%
Terminal-Bench 2.1 (AA)Artificial Analysis–65.9%
GameBench 2 OverallDuelLab GameBench 281.2†–
GameBench 2 by reasoning settingDuelLab GameBench 285.8†–
Design Arena WebsiteDesign Arena1286†1263†
FrontierCode 1.1 (AA)Artificial Analysis36.0%–
FrontierCode 2.0 (AA)Artificial Analysis42.3%–
Agents & tools
Terminal-BenchTerminal-Bench53.3%–
OSWorld-Verified 2.0OSWorld–4.6%†
APEX-AgentsMercor68.3%–
Arena AgentArena (LMArena)12–
LiveBench Long AgenticLiveBench56.2%–
LiveBench BrowserLiveBench93.1%–
LiveBench Agentic CodingLiveBench–46.9%
Terminal-Bench HardArtificial Analysis–43.9%
τ²-Bench Telecom (AA)Artificial Analysis–95.9%
Terminal-Bench 2.1 (Vals)Vals AI–53.6%†
HiL-BenchScale AI SEAL68.0%†18.7%†
GDPval-AA v2.1Artificial Analysis14761046
τ³-Banking (AA)Artificial Analysis–23.3%
ITBench SRE (AA)Artificial Analysis–31.2%
APEX-Agents (AA)Artificial Analysis–28.5%
Finance Agent v2Vals AI–44.9%†
Finance Agent v2.1Vals AI56.0%–
Harvey's Legal Agent Benchmark v1.1Vals AI1.7%–
Harvey's Legal Agent Benchmark v1Vals AI–1.7%†
Legal Research BenchVals AI26.0%15.9%†
Tax Agent BenchVals AI17.1%12.4%†
Terminal-Bench 2.0 (Vals)Vals AI–57.3%†
Terminal-Bench 4.0 (Vals)Vals AI49.5%–
Arena Agent Task CompletionArena (LMArena)9.7–
ExploitBenchEpoch AI Benchmarking Hub–18.4%†
GBAEvalEpoch AI Benchmarking Hub–0.9%†
Vending-Bench 2Andon Labs9107.5†6204.6†
SpireClimbEpoch AI Benchmarking Hub22.3%–
AutomationBenchArtificial Analysis60.2%13.0%
GDP.pdf (AA)Artificial Analysis28.6%13.0%
EnterpriseOps-GymArtificial Analysis–38.5%
AA-Briefcase v1.1Artificial Analysis1401821
GDPxGDPx by SemiAnalysis8.5%–
Design Arena AgenticDesign Arena1192†1158†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis57.6%–
MKA (AA)Artificial Analysis43.8%–
FACTS SearchGoogle92.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub90.9%57.2%†
FrontierMath Tier 4Epoch AI Benchmarking Hub92.7%25.6%†
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%96.1%†
ProofBenchVals AI–16.0%†
LiveBench MathematicsLiveBench–84.3%
AIME 2026MathArena–95.8%†
HMMT February 2026MathArena–94.7%†
USAMO 2026MathArena–51.2%†
MathArena ApexMathArena–24.0%†
Arena MathsArena (LMArena)–1479†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub57.3%34.9%†
LiveBench 2.0 Data AnalysisLiveBench82.3%–
LiveBench ResearchLiveBench79.1%–
LiveBench 1.0 Data AnalysisLiveBench–65.1%
AA-Omniscience v1.1Artificial Analysis29.6–
MMLU-ProVals AI–87.6%†
LegalBenchVals AI–84.7%†
CorpFinVals AI–66.7%†
TaxEvalVals AI–74.7%†
CaseLaw v2Vals AI–61.2%†
Excel Modeling BenchmarkVals AI–57.9%†
Excel Modeling Benchmark v1.1Vals AI73.3%–
MedCodeVals AI–40.1%†
MedScribeVals AI–78.2%†
Public Benefits Bench v1.1Vals AI–56.6%†
EBR-benchEpoch AI Benchmarking Hub78.1%2.4%†
GDP.pdfEpoch AI Benchmarking Hub–12.0%†
AA-Omniscience v1.1: accuracyArtificial Analysis47.6%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis65.5%–
FACTS ParametricGoogle70.8%†–
Instruction following
LiveBench LanguageLiveBench–75.1%
LiveBench Instruction FollowingLiveBench–64.4%
IFBenchArtificial Analysis–76.0%
MultiChallengeScale AI SEAL74.2%†–
Arena Instruction FollowingArena (LMArena)–1456†
Human preference
Arena TextArena (LMArena)–1461†
EQ-Bench 4EQ-Bench–1191†
EQ-Bench Creative Writing v3EQ-Bench–1721†
Arena Creative WritingArena (LMArena)–1432†
Arena Multi-turnArena (LMArena)–1462†
Arena Longer QueriesArena (LMArena)–1478†
Multimodal
Arena VisionArena (LMArena)–1282†
LiveBench DesignLiveBench79.7%–
MMMU-ProArtificial Analysis84.7%79.4%
MMMU-Pro (Vals)Vals AI–86.3%†
MortgageTaxVals AI–65.8%†
Blueprint-Bench 2Epoch AI Benchmarking Hub42.1%†3.9%†
Furniture AssemblyEpoch AI Benchmarking Hub79.2%21.7%†
VIALS-AAHandshake AI60.3%–
FACTS MultimodalGoogle48.8%†–
Long context
AA-LCR v1.1Artificial Analysis82.7%81.0%
Arena DocumentArena (LMArena)–1450†
MLCRArtificial Analysis30.6%11.1%
FACTS GroundingGoogle84.2%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub167.7†151.6†
LiveBench 2.0LiveBench78.8%–
LiveBench 1.0LiveBench–70.5%
AA Intelligence Index v5.0.1Artificial Analysis51.3–
AA Intelligence Index v4.3.2Artificial Analysis48.127.0
AA Progress Index v1Artificial Analysis345.2284.4
Vals IndexVals AI60.5–
Vals Finance IndexVals AI53.3%–
Vals Multimodal IndexVals AI–56.4%†
Vals Legal IndexVals AI58.8%–
Safety & honesty
FORTRESSScale AI SEAL18.2%†–
DistressBenchScale AI SEAL65.9%†–
Metadata
AA Openness IndexArtificial Analysis–33.3

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-6.1 Terra (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • Kimi K2.6 (thinking): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • GPT-6.1 Terra (max): BenchLeader Index 64.7 → 64.1.
  • GPT-6.1 Terra (max): 1 new result (Terminal-Bench).
  • Kimi K2.6 (thinking): BenchLeader Index 59.8 → 59.3.
  • GPT-6.1 Terra (max): BenchLeader Index 65.2 → 64.7.
  • GPT-6.1 Terra (max): 1 new result (MirrorCode).
  • GPT-6.1 Terra (max): 1 score revision.
  • GPT-6.1 Terra (max): 1 score revision.
  • GPT-6.1 Terra (max): 1 score revision.

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

GPT-6.1 Terra vs Kimi K2.6: questions

Is GPT-6.1 Terra better than Kimi K2.6?
GPT-6.1 Terra (max) and Kimi K2.6 (thinking) are neck and neck on quality (64.1 vs 59.3, within the ±7.4 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
GPT-6.1 Terra vs Kimi K2.6: which is cheaper, and will that change?
Kimi K2.6 is cheaper today: $1.71 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Which is faster, GPT-6.1 Terra or Kimi K2.6?
GPT-6.1 Terra streams ~2× faster (72 vs 41 output tokens per second, Artificial Analysis 7-day median).
Is GPT-6.1 Terra or Kimi K2.6 better for agents and tool use?
GPT-6.1 Terra scores higher in agentic tasks (63 vs 58 on the category index, where 50 is average).
Which is better for long documents?
They are level on long-context benchmarks (66 vs 65). GPT-6.1 Terra accepts more context: 1,050,000 against 262,144 tokens for Kimi K2.6.
More questions (3)
Which has lower latency?
Kimi K2.6 answers first: 93.1 s against 150.9 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 GPT-6.1 Terra vs Kimi K2.6?
Across the 12 benchmarks both have, GPT-6.1 Terra leads 12, Kimi K2.6 leads 0.
When was GPT-6.1 Terra released?
GPT-6.1 Terra was released on 26 Oct 2026.