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 case | Pick | Why | Confidence |
|---|---|---|---|
| Agents & tool use | GPT-6.1 Terra | 63 vs 58 category score; GDPval-AA v2.1 1476 vs 1046 | Medium |
| Long documents | Either | 66 vs 65 category score; AA-LCR v1.1 82.7% vs 81.0% | Either |
| Images and other media | GPT-6.1 Terra | 67 vs 62 category score; MMMU-Pro 84.7% vs 79.4% | Medium |
| Lowest cost | Kimi K2.6 | $1.71 vs $2.00 per 1M blended; agentic coding session $0.073 vs $0.080 | – |
| Fastest first answer | Kimi K2.6 | 93.1 s (Kimi K2.6 (thinking)) vs 150.9 s (GPT-6.1 Terra (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A 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
| Spec | GPT-6.1 Terra | Kimi K2.6 |
|---|---|---|
| Developer | OpenAI | Moonshot AI |
| Released | 26 Oct 2026 | 20 Apr 2026 |
| Context window (tokens) | 1,050,000 | 262,144 |
| Compared at | GPT-6.1 Terra (max) | Kimi K2.6 (thinking) |
| Open weights | No | Yes |
| 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.
| Category | GPT-6.1 Terra (max) | Kimi K2.6 (thinking) | Leader |
|---|---|---|---|
| Reasoning | 68.4 | – | not comparable |
| Coding | 69.3 | – | not comparable |
| Agents & tools | 63.4 | 58.4 | GPT-6.1 Terra |
| Maths | 71.7 | – | not comparable |
| Knowledge | 61.4 | – | not comparable |
| Instruction following | – | 74.1 | not comparable |
| Multimodal | 67.2 | 61.7 | GPT-6.1 Terra |
| Long context | 66.0 | 65.2 | level |
| Composite | 65.0 | – | 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.
Not drawn, measured for fewer than two of these models: Reasoning, Coding, Maths, Knowledge, Instruction following, Human preference.
Where sources disagree
Across the 12 benchmarks both have, GPT-6.1 Terra leads 12, Kimi K2.6 leads 0.
| Overall index | GPT-6.1 Terra (max) | Kimi K2.6 (thinking) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.1 | 59.3 | neck 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.
| Measure | GPT-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 reasoning | 39k | – |
| Time per task (AA Index) | 14 min | – |
| Output speed | 72 tok/s | 41 tok/s |
| Time to first answer | 150.9 s | 93.1 s |
| Time to a complete answer, last measured 13 Nov 2026 | 375.7 s | 215.8 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.
| Metric | Publisher | GPT-6.1 Terra (max) | Kimi K2.6 (thinking) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.1 | 59.3 |
| Agents & tools score | BenchLeader | 63.4 | 58.4 |
| Coding score | BenchLeader | 69.3 | – |
| Composite score | BenchLeader | 65.0 | – |
| Knowledge score | BenchLeader | 61.4 | – |
| Long context score | BenchLeader | 66.0 | 65.2 |
| Maths score | BenchLeader | 71.7 | – |
| Multimodal score | BenchLeader | 67.2 | 61.7 |
| Reasoning score | BenchLeader | 68.4 | – |
| Instruction following score | BenchLeader | – | 74.1 |
| Blended price $/M | BenchLeader | $2.00 | $1.71 |
| Output speed | BenchLeader | 72 tok/s | 41 tok/s |
| Time to first answer | BenchLeader | 150.9 s | 93.1 s |
| Context window | BenchLeader | 1,050,000 tokens | 262,144 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 94.3% | 90.8%† |
| SimpleBench | SimpleBench | 72.2%† | – |
| Arena Hard Prompts | Arena (LMArena) | – | 1485† |
| LiveBench 2.0 Reasoning | LiveBench | 88.7% | – |
| LiveBench 1.0 Reasoning | LiveBench | – | 79.4% |
| GPQA Diamond (AA) | Artificial Analysis | – | 91.1% |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.3% | 37.5% |
| HLE-Diamond (AA) | Artificial Analysis | 47.3% | – |
| GPQA Diamond (Vals) | Vals AI | – | 89.1%† |
| CritPt | Artificial Analysis | 28.0% | 8.0% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 68.0% | – |
| HLE-Diamond (Scale) | Scale AI SEAL | 35.7%† | – |
| Arena Expert | Arena (LMArena) | – | 1503† |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 20.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 74.0% | 18.0%† |
| LMCA | Epoch AI Benchmarking Hub | – | 37.3%† |
| DTBench | Epoch AI Benchmarking Hub | – | 90.9%† |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 76.7%† |
| SciCode | SciCode | 55.1% | 53.5%† |
| WeirdML | WeirdML | – | 55.9%† |
| Arena Coding | Arena (LMArena) | – | 1516† |
| Arena WebDev | Arena (LMArena) | 1678 | 1509† |
| LiveBench 2.0 Coding | LiveBench | 89.2% | – |
| LiveBench 1.0 Coding | LiveBench | – | 78.6% |
| SciCode (AA) | Artificial Analysis | 55.1% | 51.5% |
Show all 148 benchmarks
| Metric | Publisher | GPT-6.1 Terra (max) | Kimi K2.6 (thinking) |
|---|---|---|---|
| Coding | |||
| LiveCodeBench | Vals AI | – | 86.8%† |
| SWE-bench (Vals) | Vals AI | – | 76.2%† |
| Code Migration | Vals AI | – | 27.8%† |
| ProgramBench | Vals AI | – | 0.0%† |
| Vibe Code Bench v1.1 | Vals AI | 84.0% | 37.9%† |
| SWE Atlas v1.1 | Scale AI SEAL | 57.7%† | – |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | 54.0%† | – |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | 63.3%† | – |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | 55.7%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | 76.7% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2608.8 | 1092.7† |
| WeirdML v3 | WeirdML | 28.1%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 55.6% | 0.5% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 65.9% |
| GameBench 2 Overall | DuelLab GameBench 2 | 81.2† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 85.8† | – |
| Design Arena Website | Design Arena | 1286† | 1263† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 36.0% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 42.3% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 53.3% | – |
| OSWorld-Verified 2.0 | OSWorld | – | 4.6%† |
| APEX-Agents | Mercor | 68.3% | – |
| Arena Agent | Arena (LMArena) | 12 | – |
| LiveBench Long Agentic | LiveBench | 56.2% | – |
| LiveBench Browser | LiveBench | 93.1% | – |
| LiveBench Agentic Coding | LiveBench | – | 46.9% |
| Terminal-Bench Hard | Artificial Analysis | – | 43.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 95.9% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 53.6%† |
| HiL-Bench | Scale AI SEAL | 68.0%† | 18.7%† |
| GDPval-AA v2.1 | Artificial Analysis | 1476 | 1046 |
| τ³-Banking (AA) | Artificial Analysis | – | 23.3% |
| ITBench SRE (AA) | Artificial Analysis | – | 31.2% |
| APEX-Agents (AA) | Artificial Analysis | – | 28.5% |
| Finance Agent v2 | Vals AI | – | 44.9%† |
| Finance Agent v2.1 | Vals AI | 56.0% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 1.7% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 1.7%† |
| Legal Research Bench | Vals AI | 26.0% | 15.9%† |
| Tax Agent Bench | Vals AI | 17.1% | 12.4%† |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 57.3%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 49.5% | – |
| Arena Agent Task Completion | Arena (LMArena) | 9.7 | – |
| ExploitBench | Epoch AI Benchmarking Hub | – | 18.4%† |
| GBAEval | Epoch AI Benchmarking Hub | – | 0.9%† |
| Vending-Bench 2 | Andon Labs | 9107.5† | 6204.6† |
| SpireClimb | Epoch AI Benchmarking Hub | 22.3% | – |
| AutomationBench | Artificial Analysis | 60.2% | 13.0% |
| GDP.pdf (AA) | Artificial Analysis | 28.6% | 13.0% |
| EnterpriseOps-Gym | Artificial Analysis | – | 38.5% |
| AA-Briefcase v1.1 | Artificial Analysis | 1401 | 821 |
| GDPx | GDPx by SemiAnalysis | 8.5% | – |
| Design Arena Agentic | Design Arena | 1192† | 1158† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 57.6% | – |
| MKA (AA) | Artificial Analysis | 43.8% | – |
| FACTS Search | 92.7%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 90.9% | 57.2%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 92.7% | 25.6%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | 96.1%† |
| ProofBench | Vals AI | – | 16.0%† |
| LiveBench Mathematics | LiveBench | – | 84.3% |
| AIME 2026 | MathArena | – | 95.8%† |
| HMMT February 2026 | MathArena | – | 94.7%† |
| USAMO 2026 | MathArena | – | 51.2%† |
| MathArena Apex | MathArena | – | 24.0%† |
| Arena Maths | Arena (LMArena) | – | 1479† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 57.3% | 34.9%† |
| LiveBench 2.0 Data Analysis | LiveBench | 82.3% | – |
| LiveBench Research | LiveBench | 79.1% | – |
| LiveBench 1.0 Data Analysis | LiveBench | – | 65.1% |
| AA-Omniscience v1.1 | Artificial Analysis | 29.6 | – |
| MMLU-Pro | Vals AI | – | 87.6%† |
| LegalBench | Vals AI | – | 84.7%† |
| CorpFin | Vals AI | – | 66.7%† |
| TaxEval | Vals AI | – | 74.7%† |
| CaseLaw v2 | Vals AI | – | 61.2%† |
| Excel Modeling Benchmark | Vals AI | – | 57.9%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 73.3% | – |
| MedCode | Vals AI | – | 40.1%† |
| MedScribe | Vals AI | – | 78.2%† |
| Public Benefits Bench v1.1 | Vals AI | – | 56.6%† |
| EBR-bench | Epoch AI Benchmarking Hub | 78.1% | 2.4%† |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 12.0%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 47.6% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 65.5% | – |
| FACTS Parametric | 70.8%† | – | |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 75.1% |
| LiveBench Instruction Following | LiveBench | – | 64.4% |
| IFBench | Artificial Analysis | – | 76.0% |
| MultiChallenge | Scale AI SEAL | 74.2%† | – |
| Arena Instruction Following | Arena (LMArena) | – | 1456† |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1461† |
| EQ-Bench 4 | EQ-Bench | – | 1191† |
| EQ-Bench Creative Writing v3 | EQ-Bench | – | 1721† |
| Arena Creative Writing | Arena (LMArena) | – | 1432† |
| Arena Multi-turn | Arena (LMArena) | – | 1462† |
| Arena Longer Queries | Arena (LMArena) | – | 1478† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1282† |
| LiveBench Design | LiveBench | 79.7% | – |
| MMMU-Pro | Artificial Analysis | 84.7% | 79.4% |
| MMMU-Pro (Vals) | Vals AI | – | 86.3%† |
| MortgageTax | Vals AI | – | 65.8%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 42.1%† | 3.9%† |
| Furniture Assembly | Epoch AI Benchmarking Hub | 79.2% | 21.7%† |
| VIALS-AA | Handshake AI | 60.3% | – |
| FACTS Multimodal | 48.8%† | – | |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.7% | 81.0% |
| Arena Document | Arena (LMArena) | – | 1450† |
| MLCR | Artificial Analysis | 30.6% | 11.1% |
| FACTS Grounding | 84.2%† | – | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 167.7† | 151.6† |
| LiveBench 2.0 | LiveBench | 78.8% | – |
| LiveBench 1.0 | LiveBench | – | 70.5% |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 51.3 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 48.1 | 27.0 |
| AA Progress Index v1 | Artificial Analysis | 345.2 | 284.4 |
| Vals Index | Vals AI | 60.5 | – |
| Vals Finance Index | Vals AI | 53.3% | – |
| Vals Multimodal Index | Vals AI | – | 56.4%† |
| Vals Legal Index | Vals AI | 58.8% | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 18.2%† | – |
| DistressBench | Scale AI SEAL | 65.9%† | – |
| Metadata | |||
| AA Openness Index | Artificial 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.
Related comparisons
- GPT-6.1 Terra vs Claude Fable 5.2
- GPT-6.1 Terra vs Gemini 4 Carbon
- GPT-6.1 Terra vs Claude Opus 5.5
- GPT-6.1 Terra vs GPT-6 Astra
- Kimi K2.6 vs Claude Opus 5.5
- GPT-6.1 Terra vs Claude Fable 5.1
- GPT-6.1 Terra vs GPT-6.1 Sol
- GPT-6.1 Terra vs Claude Fable 5
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.