# Kimi K3.1 Pro vs Kimi K3

> Side-by-side benchmark comparison for Kimi K3.1 Pro and Kimi K3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-3-1-pro-vs-kimi-k3
- Last updated: October 23, 2026

- Shared sourced benchmarks: 18
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Kimi K3.1 Pro if you want the stronger benchmark profile. Kimi K3 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Kimi K3.1 Pro leads overall 82 to 69.93.
- The clearest category separation is in multimodal & grounded, where the averages are 98 for Kimi K3.1 Pro and 90.2 for Kimi K3.
- The biggest single benchmark swing is APEX-Agents in Agentic, with scores of 67.2% and 37.6%.
- Kimi K3.1 Pro is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Kimi K3.1 Pro | Kimi K3 |
|----------|----------|----------|
| Creator | Moonshot AI | Moonshot AI |
| Type | Pending | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 1.05M | 1.05M |
| Overall Score | null | 69.93 |
| Benchmarks Covered | 42 | 53 |
| Pricing (input/output) | $2.00 / $10.00 | $3.00 / $15.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K3 public-lane score: 69.3 (Supported · #10/132)

| Benchmark | Kimi K3.1 Pro | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 65.70% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 | 38.1% | Coming soon | Coming soon |
| HLE w/ tools | 70.0% | Coming soon | Coming soon |
| BrowseComp | 92.1% | 91.2% | Kimi K3.1 Pro |
| BioMysteryBench | 80.6% | Coming soon | Coming soon |
| Agents' Last Exam | 43.2% | Coming soon | Coming soon |
| Agents' Last Exam (CLI) | 44.2% | Coming soon | Coming soon |
| APEX-Agents | 67.2% | 37.6% | Kimi K3.1 Pro |
| Frontier Finance | 58.6% | Coming soon | Coming soon |
| HANDBOOK.md | 44.6% | Coming soon | Coming soon |
| OSWorld 2.0 | 79.6% | Coming soon | Coming soon |
| Business Operation | 37.8% | Coming soon | Coming soon |
| Financial Modeling | 57.6% | Coming soon | Coming soon |
| Financial Research | 70.4% | Coming soon | Coming soon |
| Kimi Hallu Bench Hard (tools) | 8.3% | Coming soon | Coming soon |
| ExploitGym | 20.7% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 88.3% | Coming soon |
| DeepSearchQA | Coming soon | 95.0% | Coming soon |
| Toolathlon-Verified | Coming soon | 73.2% | Coming soon |
| MCP Atlas | Coming soon | 84.2% | Coming soon |
| AutomationBench | Coming soon | 30.8% | Coming soon |
| JobBench | Coming soon | 52.9% | Coming soon |
| SpreadsheetBench 2 | Coming soon | 34.8% | Coming soon |
| DECK-Bench | Coming soon | 73.5% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 80.9% | Coming soon |
| ApprenticeBench | Coming soon | 18% | Coming soon |
| Hermes Index | Coming soon | 39.2% | Coming soon |
| Hermes Bench | Coming soon | 71.5% | Coming soon |
| MazeBench | Coming soon | 1% | Coming soon |

### Coding

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K3 public-lane score: 58.8 (Supported · #23/153)

| Benchmark | Kimi K3.1 Pro | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| DeepSWE | 75.5% | 67.5% | Kimi K3.1 Pro |
| ProgramBench (binary) | 31.5% | Coming soon | Coming soon |
| Kimi Code Bench v2 | 77.1% | 72.9% | Kimi K3.1 Pro |
| Kimi Code Bench 3.0 Long-horizon | 61.2% | Coming soon | Coming soon |
| sweMarathon | 51.7% | 42% | Kimi K3.1 Pro |
| PostTrainBench v1.2 | 36.5% | Coming soon | Coming soon |
| CursorBench 3.2 | Coming soon | 60.8% | Coming soon |
| FrontierSWE | Coming soon | 81.2% | Coming soon |
| ProgramBench | Coming soon | 77.8% | Coming soon |
| PostTrain Bench | Coming soon | 36.6% | Coming soon |
| MLS-Bench Lite | Coming soon | 48.3% | Coming soon |
| VulcanBench v3 | Coming soon | 73.7% | Coming soon |
| OpenHarmony Bench | Coming soon | 57.3% | Coming soon |
| FrontierSWE v2 | Coming soon | 25.9% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 87.2% | Coming soon |
| SWE-bench (Vals) | Coming soon | 93.4% | Coming soon |
| PostTrainBench v1.1 | Coming soon | 32.0% | Coming soon |
| Bug Hunt Bench | Coming soon | 21.0 fixes | Coming soon |

### Reasoning

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K3 public-lane score: 69.8 (#18/27)

| Benchmark | Kimi K3.1 Pro | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | Coming soon | 94.50% | Coming soon |
| ARC-AGI-2 | Coming soon | 60.4% | Coming soon |

### Multimodal & Grounded

- Winner: Kimi K3.1 Pro
- Kimi K3.1 Pro public-lane score: 98 (#1/56)
- Kimi K3 public-lane score: 90.2 (#5/56)

| Benchmark | Kimi K3.1 Pro | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | 67.4% | 63.3% | Kimi K3.1 Pro |
| OfficeQA Pro v2 | 64.4% | Coming soon | Coming soon |
| BenchCAD Vision2Code (no tools) | 0.728 | Coming soon | Coming soon |
| BenchCAD Vision2Code (tools) | 0.927 | Coming soon | Coming soon |
| MMMU-Pro | 84.1% | 81.6% | Kimi K3.1 Pro |
| MMMU-Pro w/ Python | 90% | 83.4% | Kimi K3.1 Pro |
| CharXiv | 93.4% | 91.3% | Kimi K3.1 Pro |
| CharXiv w/o tools | 89% | 84.8% | Kimi K3.1 Pro |
| Chartography (tools) | 90.2% | Coming soon | Coming soon |
| BabyVision w/ Python | 95.4% | 85.7% | Kimi K3.1 Pro |
| ZeroBench | 39.0% | 23.0% | Kimi K3.1 Pro |
| ZeroBench w/ Python | 63.0% | 41.0% | Kimi K3.1 Pro |
| GDP.pdf (Gemini judge) | 34.6% | Coming soon | Coming soon |
| GDP.pdf w/ Python (Gemini judge) | 85.7% | Coming soon | Coming soon |
| PerceptionBench | 68.3% | 58.5% | Kimi K3.1 Pro |
| ExtractBench (LlamaIndex) | Coming soon | 83.17% | Coming soon |
| MathVision | Coming soon | 94.3% | Coming soon |
| MathVision w/ Python | Coming soon | 97.8% | Coming soon |
| WorldVQA ForceAnswer | Coming soon | 51.0% | Coming soon |
| OmniDocBench | Coming soon | 91.1% | Coming soon |

### Knowledge

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K3 public-lane score: 67.5 (Supported · #24/187)

| Benchmark | Kimi K3.1 Pro | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 94.2% | 93.5% | Kimi K3.1 Pro |
| GPQA-D | 94.2% | 93.5% | Kimi K3.1 Pro |
| HLE | 70% | 56% | Kimi K3.1 Pro |
| HLE w/o tools | 51.1% | 43.5% | Kimi K3.1 Pro |
| Kimi Hallu Bench | 5.4% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 92.9% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 88.0% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K3 public-lane score: Coming soon

| Benchmark | Kimi K3.1 Pro | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | Coming soon | 52.7% | Coming soon |

## FAQ

### Which is better overall, Kimi K3.1 Pro or Kimi K3?

Kimi K3.1 Pro is ahead overall on BenchLM right now.

### Where is the biggest gap between Kimi K3.1 Pro and Kimi K3?

The widest category gap is in multimodal & grounded, where the averages are 98 for Kimi K3.1 Pro and 90.2 for Kimi K3.

### How many benchmarks does Kimi K3.1 Pro cover on BenchLM?

Kimi K3.1 Pro currently has 42 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K3 cover on BenchLM?

Kimi K3 currently has 53 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Kimi K3.1 Pro vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-3-1-pro)
- [Kimi K3 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k3)
- [Kimi K3.1 Pro vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-kimi-3-1-pro)
- [Kimi K3 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-kimi-k3)

## Explore More

- [Kimi K3.1 Pro profile](/models/kimi-3-1-pro)
- [Kimi K3 profile](/models/kimi-k3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)