Kimi K3 vs Kimi K3.1 Pro
Full profiles: Kimi K3 (Moonshot AI) and Kimi K3.1 Pro (Moonshot AI): every benchmark, price and rank.
Updated · Data from 10 sources
As of 24 Oct 2026, Kimi K3 (max) and Kimi K3.1 Pro are neck and neck on quality (64.7 vs 66.8 on the BenchLeader Index, inside the ±7.0 margin of error), and Kimi K3.1 Pro costs 1.5× less, which makes it the better buy for most workloads. Pick Kimi K3 for long context (70 vs 68); pick Kimi K3.1 Pro for reasoning (81 vs 66).
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 |
|---|---|---|---|
| Agents & tool use | Kimi K3.1 Pro | 67 vs 59 category score; CWE-Bench (AA) 60.8% vs 53.3% | High |
| Reasoning | Kimi K3.1 Pro | 81 vs 66 category score; CritPt 24.6% vs 23.4% | High |
| Knowledge | Kimi K3.1 Pro | 75 vs 63 category score; AA-Omniscience 29.5 vs 19.7 | High |
| Long documents | Kimi K3 | 70 vs 68 category score; AA-LCR 88.7% vs 86.3% | Medium |
| Images and other media | Kimi K3.1 Pro | 67 vs 64 category score; MMMU-Pro 83.9% vs 80.5% | Medium |
| Chat quality (human preference) | – | Only Kimi K3 has an Arena rating (68 category score) | Not comparable |
| Lowest cost | Kimi K3.1 Pro | $4.00 vs $6.00 per 1M blended; agentic coding session $0.160 vs $0.240 | – |
| Fastest first answer | Kimi K3.1 Pro | 27.7 s (Kimi K3.1 Pro) vs 55.4 s (Kimi K3 (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
- Kimi K3 (max) and Kimi K3.1 Pro are neck and neck on quality (64.7 vs 66.8, within the ±7.0 margin).
- Kimi K3 (max) is stronger in coding, composite, human preference, long context, maths.
- Kimi K3.1 Pro is stronger in agents & tools, knowledge, multimodal, reasoning.
- Kimi K3.1 Pro is 1.5× cheaper ($4.00 vs $6.00 per 1M blended).
- Kimi K3.1 Pro streams 2.1× faster (81 vs 39 tokens per second).
At a glance
| Spec | Kimi K3 | Kimi K3.1 Pro |
|---|---|---|
| Developer | Moonshot AI | Moonshot AI |
| Released | 16 Jul 2026 | 23 Oct 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Kimi K3 (max) | Kimi K3.1 Pro |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $3.00 / $15.00 / $0.300 | $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.
| Category | Kimi K3 (max) | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Reasoning | 66.4 | 81.3 | Kimi K3.1 Pro |
| Coding | 64.6 | – | not comparable |
| Agents & tools | 58.9 | 67.3 | Kimi K3.1 Pro |
| Maths | 63.4 | – | not comparable |
| Knowledge | 62.8 | 74.8 | Kimi K3.1 Pro |
| Human preference | 68.1 | – | not comparable |
| Multimodal | 63.6 | 67.0 | Kimi K3.1 Pro |
| Long context | 69.6 | 68.3 | Kimi K3 |
| Composite | 78.3 | 75.8 | Kimi K3 |
Where sources disagree
Across the 17 benchmarks both have, Kimi K3 leads 1, Kimi K3.1 Pro leads 16. Every overall index that rates both puts Kimi K3.1 Pro ahead.
| Overall index | Kimi K3 (max) | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 64.7 | 66.8 | neck and neck |
| AA Intelligence Index v4.3.2 | 43.6 | 55.1 | Kimi K3.1 Pro |
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 | Kimi K3 (max) | Kimi K3.1 Pro |
|---|---|---|
| Blended price per 1M tokens | $6.00 | $4.00 |
| Input / output per 1M | $3.00 / $15.00 | $2.00 / $10.00 |
| Cached input per 1M | $0.300 | $0.200 |
| Price per task: chat reply | $0.0057 | $0.0038 |
| Price per task: summarize a 30-page report | $0.045 | $0.030 |
| Price per task: code edit | $0.041 | $0.027 |
| Price per task: agentic coding session | $0.240 | $0.160 |
| Price per task: structured extraction | $0.0090 | $0.0060 |
| Cost to run a full benchmark suite | $2.00 | $2.11 |
| Output speed | 39 tok/s | 81 tok/s |
| Time to first answer | 55.4 s | 27.7 s |
| Time to a complete answer | 68.4 s | 33.9 s |
Per token is not per task: on Artificial Analysis' full suite Kimi K3 (max) cost $2.00 and Kimi K3.1 Pro $2.11, because Kimi K3.1 Pro used about 1.6× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. Kimi K3 (max) scores 64.7 and takes 55 s to its first answer token; Kimi K3 scores 59.1 in 1 s, Kimi K3 (low) scores 58.2 in 57 s. Kimi K3.1 Pro scores 66.8 and takes 28 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
133 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 | Kimi K3 (max) | Kimi K3.1 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.7 | 66.8 |
| Agents & tools score | BenchLeader | 58.9 | 67.3 |
| Coding score | BenchLeader | 64.6 | – |
| Composite score | BenchLeader | 78.3 | 75.8 |
| Human preference score | BenchLeader | 68.1 | – |
| Knowledge score | BenchLeader | 62.8 | 74.8 |
| Long context score | BenchLeader | 69.6 | 68.3 |
| Maths score | BenchLeader | 63.4 | – |
| Multimodal score | BenchLeader | 63.6 | 67.0 |
| Reasoning score | BenchLeader | 66.4 | 81.3 |
| Blended price $/M | BenchLeader | $6.00 | $4.00 |
| Output speed | BenchLeader | 39 tok/s | 81 tok/s |
| Time to first answer | BenchLeader | 55.4 s | 27.7 s |
| Context window | BenchLeader | 1,048,576 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 | 90.7%† | 91.1% |
| LiveBench 1.0 Reasoning | LiveBench | 90.7%† | – |
| GPQA Diamond (AA) | Artificial Analysis | 93.5% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.9% | 52.5% |
| GPQA Diamond (Vals) | Vals AI | 92.9%† | – |
| ARC-AGI-1 | ARC Prize | 94.5% | – |
| ARC-AGI-2 | ARC Prize | 60.4% | – |
| CritPt | Artificial Analysis | 23.4% | 24.6% |
| 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 | 59.3%† | 81.8% |
| LiveBench 1.0 Coding | LiveBench | 81.5%† | – |
| SciCode (AA) | Artificial Analysis | 59.5% | 60.8% |
| LiveCodeBench | Vals AI | 87.2% | – |
Show all 133 benchmarks
| Metric | Publisher | Kimi K3 (max) | Kimi K3.1 Pro |
|---|---|---|---|
| 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 | 12.6% | 67.2% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 85.0% | – |
| Startrise Frontend | Startrise | 79.8%† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 43.6% | 47.1% |
| Agents & tools | |||
| APEX-Agents | Mercor | 47.8%† | – |
| Arena Agent | Arena (LMArena) | 1.8 | – |
| LiveBench Long Agentic | LiveBench | 42.8%† | 49.5% |
| LiveBench Browser | LiveBench | 16.0%† | 80.0% |
| 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% | – |
| GDPval-AA v2.1 | Artificial Analysis | – | 67.3% |
| 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 | 58.3% | 73.3% |
| GDP.pdf (AA) | Artificial Analysis | 22.0% | 31.4% |
| Harvey LAB-AA v1.1 | Harvey | 5.3% | – |
| EnterpriseOps-Gym | Artificial Analysis | 45.3% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1499 | 1678 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 8.1% | – |
| CWE-Bench (AA) | Artificial Analysis | 53.3% | 60.8% |
| DeepSec-Bench (AA) | Artificial Analysis | 12.4% | 36.7% |
| CyberGym end-to-end (AA) | Artificial Analysis | 58.0% | 94.7% |
| 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 | 78.7%† | 79.1% |
| LiveBench Research | LiveBench | 79.0%† | 77.9% |
| LiveBench 1.0 Data Analysis | LiveBench | 78.7%† | – |
| AA-Omniscience | Artificial Analysis | 19.7 | 29.5 |
| 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 | 47.6% | 51.0% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 46.8% | 56.1% |
| 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 | 1339† | – |
| Arena Creative Writing | Arena (LMArena) | 1462 | – |
| Arena Multi-turn | Arena (LMArena) | 1502 | – |
| Arena Longer Queries | Arena (LMArena) | 1503 | – |
| Multimodal | |||
| LiveBench Design | LiveBench | 77.2%† | 77.8% |
| MMMU-Pro | Artificial Analysis | 80.5% | 83.9% |
| 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 | 981 | – |
| Long context | |||
| AA-LCR | Artificial Analysis | 88.7% | 86.3% |
| MLCR | Artificial Analysis | 21.7% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 157.9† | – |
| LiveBench 2.0 | LiveBench | 63.4%† | 76.7% |
| LiveBench 1.0 | LiveBench | 79.2%† | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 43.6 | 55.1 |
| 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 | 64.1 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 26.6% | – |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 38.9 | – |
Data as of 2026-10-24. Best configuration of each model; every score links to its source on the model pages.
What changed
- Kimi K3.1 Pro: BenchLeader Index 65.6 → 66.8.
- Kimi K3.1 Pro: 5 new results (FrontierCode 1.1 (AA), AA Cyber Index, CWE-Bench (AA)…).
- Kimi K3 (max): 7 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).
- Kimi K3.1 Pro: first results.
- 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.
Related comparisons
- Kimi K3 vs Claude Opus 5.5
- Kimi K3 vs Gemini 4 Argon
- Kimi K3 vs Muse Wonder Full
- Kimi K3.1 Pro vs Claude Opus 5.5
- Kimi K3.1 Pro vs Gemini 4 Argon
- Kimi K3.1 Pro vs Muse Wonder Full
- Kimi K3.1 Pro vs Claude Fable 5.1
- Kimi K3 vs GPT-6 Astra
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Kimi K3 vs Kimi K3.1 Pro: questions
- Is Kimi K3 better than Kimi K3.1 Pro?
- Kimi K3 (max) and Kimi K3.1 Pro are neck and neck on quality (64.7 vs 66.8, within the ±7.0 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-24, so check the category scores for your use.
- Which is cheaper, Kimi K3 or Kimi K3.1 Pro, and will that change?
- Kimi K3.1 Pro is cheaper today: $4.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Kimi K3 better than Kimi K3.1 Pro for agents and tool use?
- Kimi K3.1 Pro scores higher in agentic tasks (67 vs 59 on the category index, where 50 is average). On CWE-Bench (AA), the top shared agents & tools benchmark, it is 53.3% for Kimi K3 against 60.8% for Kimi K3.1 Pro.
- Which is better for long documents?
- Kimi K3 scores higher on long-context benchmarks (70 vs 68). Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Kimi K3.1 Pro answers first: 27.7 s against 55.4 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, Kimi K3 or Kimi K3.1 Pro?
- Kimi K3.1 Pro streams faster: 81 against 39 output tokens per second.
- Do independent benchmarks agree on Kimi K3 vs Kimi K3.1 Pro?
- Across the 17 benchmarks both have, Kimi K3 leads 1, Kimi K3.1 Pro leads 16. Every overall index that rates both puts Kimi K3.1 Pro ahead.
- When was Kimi K3.1 Pro released?
- Kimi K3.1 Pro was released on 23 Oct 2026.