GPT-6.1 Terra vs Kimi K3
Full profiles: GPT-6.1 Terra (OpenAI) and Kimi K3 (Moonshot AI): every benchmark, price and rank.
Updated · Data from 9 sources
As of 27 Oct 2026, GPT-6.1 Terra (max) and Kimi K3 (max) are neck and neck on quality (65.9 vs 64.6 on the BenchLeader Index, inside the ±7.7 margin of error), and GPT-6.1 Terra (max) costs 3.0× less, which makes it the better buy for most workloads. Pick GPT-6.1 Terra for reasoning (86 vs 66); pick Kimi K3 for long context (69 vs 66).
GPT-6.1 Terra benchmarks 
Kimi K3 benchmarks 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 |
|---|---|---|---|
| Reasoning | GPT-6.1 Terra | 86 vs 66 category score; CritPt 28.0% vs 23.4% | High |
| Knowledge | GPT-6.1 Terra | 75 vs 63 category score; AA-Omniscience 29.8 vs 19.7 | High |
| Long documents | Kimi K3 | 69 vs 66 category score; AA-LCR 88.7% vs 82.7% | Medium |
| Images and other media | GPT-6.1 Terra | 68 vs 63 category score; MMMU-Pro 84.7% vs 80.5% | Medium |
| Chat quality (human preference) | – | Only Kimi K3 has an Arena rating (68 category score) | Not comparable |
| Lowest cost | GPT-6.1 Terra | $2.00 vs $6.00 per 1M blended; agentic coding session $0.080 vs $0.240 | – |
| Fastest first answer | Kimi K3 | 39.4 s (Kimi K3 (max)) vs 131.8 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 K3 (max) are neck and neck on quality (65.9 vs 64.6, within the ±7.7 margin).
- GPT-6.1 Terra (max) is stronger in composite, knowledge, multimodal, reasoning.
- Kimi K3 (max) is stronger in long context, agents & tools, coding, human preference, maths.
- GPT-6.1 Terra (max) is 3.0× cheaper ($2.00 vs $6.00 per 1M blended).
- GPT-6.1 Terra (max) streams 1.7× faster (91 vs 55 tokens per second).
At a glance
| Spec | GPT-6.1 Terra | Kimi K3 |
|---|---|---|
| Developer | OpenAI | Moonshot AI |
| Released | 26 Oct 2026 | 16 Jul 2026 |
| Context window (tokens) | 1,050,000 | 1,048,576 |
| Compared at | GPT-6.1 Terra (max) | Kimi K3 (max) |
| Open weights | No | Yes |
| Price in / out / cached input per 1M | $1.00 / $5.00 / $0.050 | $3.00 / $15.00 / $0.300 |
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 K3 (max) | Leader |
|---|---|---|---|
| Reasoning | 86.2 | 66.3 | GPT-6.1 Terra |
| Coding | – | 64.5 | not comparable |
| Agents & tools | – | 59.4 | not comparable |
| Maths | – | 63.4 | not comparable |
| Knowledge | 74.5 | 62.7 | GPT-6.1 Terra |
| Human preference | – | 68.1 | not comparable |
| Multimodal | 67.5 | 63.2 | GPT-6.1 Terra |
| Long context | 66.3 | 69.4 | Kimi K3 |
| Composite | 82.8 | 77.7 | GPT-6.1 Terra |
Where sources disagree
Across the 14 benchmarks both have, GPT-6.1 Terra leads 9, Kimi K3 leads 5. Every overall index that rates both puts GPT-6.1 Terra ahead.
| Overall index | GPT-6.1 Terra (max) | Kimi K3 (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 65.9 | 64.6 | neck and neck |
| AA Intelligence Index v4.3.2 | 48.1 | 43.6 | GPT-6.1 Terra |
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.
| Measure | GPT-6.1 Terra (max) | Kimi K3 (max) |
|---|---|---|
| Blended price per 1M tokens | $2.00 | $6.00 |
| Input / output per 1M | $1.00 / $5.00 | $3.00 / $15.00 |
| Cached input per 1M | $0.050 | $0.300 |
| Price per task: chat reply | $0.0019 | $0.0057 |
| Price per task: summarize a 30-page report | $0.015 | $0.045 |
| Price per task: code edit | $0.013 | $0.041 |
| Price per task: agentic coding session | $0.080 | $0.240 |
| Price per task: structured extraction | $0.0030 | $0.0090 |
| Cost to run a full benchmark suite | $0.403 | $2.00 |
| Output speed | 91 tok/s | 55 tok/s |
| Time to first answer | 131.8 s | 39.4 s |
| Time to a complete answer | 137.3 s | 48.5 s |
Per token is not per task: on Artificial Analysis' full suite GPT-6.1 Terra (max) cost $0.403 and Kimi K3 (max) $2.00, because Kimi K3 (max) used about 1.7× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Terra (max) scores 65.9 and takes 132 s to its first answer token; GPT-6.1 Terra (xhigh) scores 65.0 in 18 s, GPT-6.1 Terra (high) scores 64.7 in 7 s. Kimi K3 (max) scores 64.6 and takes 39 s to its first answer token; Kimi K3 scores 59.2 in 1 s, Kimi K3 (low) scores 58.1 in 39 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
132 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 K3 (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 65.9 | 64.6 |
| Composite score | BenchLeader | 82.8 | 77.7 |
| Knowledge score | BenchLeader | 74.5 | 62.7 |
| Long context score | BenchLeader | 66.3 | 69.4 |
| Multimodal score | BenchLeader | 67.5 | 63.2 |
| Reasoning score | BenchLeader | 86.2 | 66.3 |
| Agents & tools score | BenchLeader | – | 59.4 |
| Coding score | BenchLeader | – | 64.5 |
| Human preference score | BenchLeader | – | 68.1 |
| Maths score | BenchLeader | – | 63.4 |
| Blended price $/M | BenchLeader | $2.00 | $6.00 |
| Output speed | BenchLeader | 91 tok/s | 55 tok/s |
| Time to first answer | BenchLeader | 131.8 s | 39.4 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 93.1% |
| SimpleBench | SimpleBench | – | 60.7% |
| Arena Hard Prompts | Arena (LMArena) | – | 1516 |
| LiveBench 2.0 Reasoning | LiveBench | 88.7%† | 90.7%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 90.7%† |
| GPQA Diamond (AA) | Artificial Analysis | – | 93.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.3% | 46.9% |
| GPQA Diamond (Vals) | Vals AI | – | 92.9%† |
| ARC-AGI-1 | ARC Prize | – | 94.5% |
| ARC-AGI-2 | ARC Prize | – | 60.4% |
| CritPt | Artificial Analysis | 28.0% | 23.4% |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 36.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 26.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 52.7% |
| DTBench | Epoch AI Benchmarking Hub | – | 91.2% |
| ForecastBench | ForecastBench | – | 64.6% |
| Coding | |||
| SciCode | SciCode | – | 59.5% |
| WeirdML | WeirdML | – | 82.6% |
| FrontierCode | Cognition | – | 44.2%† |
| Arena Coding | Arena (LMArena) | – | 1539 |
| Arena WebDev | Arena (LMArena) | – | 1655 |
| LiveBench 2.0 Coding | LiveBench | 90.8%† | 59.3%† |
| LiveBench 1.0 Coding | LiveBench | – | 81.5%† |
| SciCode (AA) | Artificial Analysis | 55.1% | 59.5% |
| LiveCodeBench | Vals AI | – | 87.2% |
Show all 132 benchmarks
| Metric | Publisher | GPT-6.1 Terra (max) | Kimi K3 (max) |
|---|---|---|---|
| Coding | |||
| IOI | Vals AI | – | 48.9% |
| SWE-bench (Vals) | Vals AI | – | 93.4%† |
| Code Migration | Vals AI | – | 16.1% |
| Code Migration v1.1 | Vals AI | – | 28.6% |
| ProgramBench | Vals AI | – | 2.0%† |
| SWE-bench Multimodal | Vals AI | – | 44.2% |
| Vibe Code Bench 1-100 | Vals AI | – | 18.2% |
| Vibe Code Bench v1.1 | Vals AI | – | 85.0% |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | – | 93.0% |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 68.5% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1524.5 |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 25.9% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 55.6% | 12.6% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 85.0% |
| Startrise Frontend | Startrise | – | 79.8%† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 36.0% | 43.6% |
| Agents & tools | |||
| APEX-Agents | Mercor | – | 47.8%† |
| Arena Agent | Arena (LMArena) | – | 1.6 |
| LiveBench Long Agentic | LiveBench | 48.6%† | 26.4%† |
| LiveBench Browser | LiveBench | 93.1%† | 75.2%† |
| LiveBench Agentic Coding | LiveBench | – | 62.2%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 80.9%† |
| MCP Atlas | Scale AI SEAL | – | 82.3% |
| HiL-Bench | Scale AI SEAL | – | 42.7%† |
| τ³-bench Banking | τ²-bench | – | 37.1% |
| τ³-Banking (AA) | Artificial Analysis | – | 46.0% |
| ITBench SRE (AA) | Artificial Analysis | – | 47.7% |
| Analyst Agent (AA) | Artificial Analysis | – | 38.8% |
| APEX-Agents (AA) | Artificial Analysis | – | 41.3% |
| CyberBench | Vals AI | – | 75.2% |
| Finance Agent v2 | Vals AI | – | 53.1% |
| Finance Agent v2.1 | Vals AI | – | 60.0% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 12.9% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 12.9% |
| Legal Research Bench | Vals AI | – | 46.1% |
| Tax Agent Bench | Vals AI | – | 33.4% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 17.2% |
| Terminal-Bench Science | Vals AI | – | 1.4% |
| Time Horizon Index: KSP | Vals AI | – | 10.5% |
| PostTrainBench | Epoch AI Benchmarking Hub | – | 32.0%† |
| GBAEval | Epoch AI Benchmarking Hub | – | 48.4%† |
| Vending-Bench 2 | Andon Labs | – | 5165.0† |
| AutomationBench | Artificial Analysis | 60.2% | 58.3% |
| GDP.pdf (AA) | Artificial Analysis | 28.6% | 22.0% |
| Harvey LAB-AA v1.1 | Harvey | – | 5.3% |
| EnterpriseOps-Gym | Artificial Analysis | – | 45.3% |
| AA-Briefcase v1.1 | Artificial Analysis | 1402 | 1499 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 57.6% | 8.1% |
| CWE-Bench (AA) | Artificial Analysis | – | 53.3% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 12.4% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 58.0% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 72.2% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 39.0% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 97.2% |
| ProofBench | Vals AI | – | 87.0%† |
| LiveBench Mathematics | LiveBench | – | 84.4%† |
| AIME 2026 | MathArena | – | 96.7%† |
| HMMT February 2026 | MathArena | – | 97.0%† |
| MathArena Apex | MathArena | – | 65.6%† |
| Arena Maths | Arena (LMArena) | – | 1499 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 50.6% |
| LiveBench 2.0 Data Analysis | LiveBench | 82.3%† | 78.7%† |
| LiveBench Research | LiveBench | 73.9%† | 79.0%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 78.7%† |
| AA-Omniscience | Artificial Analysis | 29.8 | 19.7 |
| MMLU-Pro | Vals AI | – | 88.0% |
| LegalBench | Vals AI | – | 86.2% |
| CorpFin | Vals AI | – | 71.6%† |
| TaxEval | Vals AI | – | 75.7%† |
| BioMysteryBench | Vals AI | – | 72.6% |
| Excel Modeling Benchmark | Vals AI | – | 66.7% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 71.3% |
| MedCode | Vals AI | – | 49.4% |
| MedScribe | Vals AI | – | 88.0% |
| Public Benefits Bench v1.1 | Vals AI | – | 68.2% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 19.0% |
| AA-Omniscience: accuracy | Artificial Analysis | 49.1% | 47.6% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 62.0% | 46.8% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 85.5%† |
| LiveBench Instruction Following | LiveBench | – | 71.4%† |
| Arena Instruction Following | Arena (LMArena) | – | 1489 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1487 |
| EQ-Bench 4 | EQ-Bench | – | 1318† |
| Arena Creative Writing | Arena (LMArena) | – | 1462 |
| Arena Multi-turn | Arena (LMArena) | – | 1502 |
| Arena Longer Queries | Arena (LMArena) | – | 1503 |
| Multimodal | |||
| LiveBench Design | LiveBench | 82.3%† | 77.2%† |
| MMMU-Pro | Artificial Analysis | 84.7% | 80.5% |
| MMMU-Pro (Vals) | Vals AI | – | 88.2%† |
| MortgageTax | Vals AI | – | 66.3%† |
| SAGE | Vals AI | – | 52.8% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 29.5%† |
| AA-3D | Artificial Analysis | – | 982 |
| Long context | |||
| AA-LCR | Artificial Analysis | 82.7% | 88.7% |
| MLCR | Artificial Analysis | – | 21.7% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 157.9† |
| LiveBench 2.0 | LiveBench | 77.2%† | 64.6%† |
| LiveBench 1.0 | LiveBench | – | 79.2%† |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 48.1 | 43.6 |
| Vals Index | Vals AI | – | 53.0 |
| Vals Finance Index | Vals AI | – | 58.0% |
| Vals RSI Index | Vals AI | – | 20.9% |
| Vals Multimodal Index | Vals AI | – | 73.4%† |
| Vals Router Index | Vals AI | – | 53.0%† |
| AA Cyber Index | Artificial Analysis | – | 41.3 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 18.2%† | 26.6% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 38.9 |
Data as of 2026-10-27. Best configuration of each model; every score links to its source on the model pages.
What changed
- Kimi K3 (max): 7 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).
- Kimi K3 (max): 1 new result (Terminal-Bench-Science 0.1 (AA)); 1 score revision.
- Kimi K3 (max): 3 score revisions.
- Kimi K3 (max): 1 score revision.
- Kimi K3 (max): 1 new result (τ³-bench Banking).
- Kimi K3 (max): 8 new results (LegalBench, Vals Index, Finance Agent v2…); 5 score revisions.
- Kimi K3 (max): 3 score revisions.
- Kimi K3 (max): 1 score revision.
- Kimi K3 (max): BenchLeader Index 65.7 → 64.9.
- Kimi K3 (max): 6 new results (FrontierCode 1.1 (AA), AA Cyber Index, CWE-Bench (AA)…).
Related comparisons
- GPT-6.1 Terra vs Claude Opus 5.5
- GPT-6.1 Terra vs Claude Fable 5.1
- GPT-6.1 Terra vs GPT-6 Astra
- Kimi K3 vs Claude Opus 5.5
- Kimi K3 vs Claude Fable 5.1
- Kimi K3 vs GPT-6 Astra
- Kimi K3 vs Muse Wonder Full
- GPT-6.1 Sol vs Kimi K3
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GPT-6.1 Terra vs Kimi K3: questions
- Is GPT-6.1 Terra better than Kimi K3?
- GPT-6.1 Terra (max) and Kimi K3 (max) are neck and neck on quality (65.9 vs 64.6, within the ±7.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-27, so check the category scores for your use.
- Which is cheaper, GPT-6.1 Terra or Kimi K3, and will that change?
- GPT-6.1 Terra is cheaper today: $2.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Which is better for long documents?
- Kimi K3 scores higher on long-context benchmarks (69 vs 66). Both take about 1.1M tokens: GPT-6.1 Terra 1,050,000, Kimi K3 1,048,576.
- Which has lower latency?
- Kimi K3 (max) answers first: 39.4 s against 131.8 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.
- Which is faster, GPT-6.1 Terra or Kimi K3?
- GPT-6.1 Terra streams faster: 91 against 55 output tokens per second.
- Do independent benchmarks agree on GPT-6.1 Terra vs Kimi K3?
- Across the 14 benchmarks both have, GPT-6.1 Terra leads 9, Kimi K3 leads 5. Every overall index that rates both puts GPT-6.1 Terra ahead.
- When was GPT-6.1 Terra released?
- GPT-6.1 Terra was released on 26 Oct 2026.