# Kimi K2.7 Code vs Kimi K3

> Side-by-side benchmark comparison for Kimi K2.7 Code and Kimi K3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-k2-7-code-vs-kimi-k3
- Last updated: October 2, 2026

- Shared sourced benchmarks: 9
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Kimi K3 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Kimi K3 has the higher overall point estimate 72.14 to 54.6. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 37.6 for Kimi K2.7 Code and 68.1 for Kimi K3.
- The biggest single benchmark swing is ProgramBench in Coding, with scores of 53.6% and 77.8%.
- Kimi K2.7 Code is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Kimi K3 also has the larger context window at 1.05M.

## Model Snapshot

| Property | Kimi K2.7 Code | Kimi K3 |
|----------|----------|----------|
| Creator | Moonshot AI | Moonshot AI |
| Type | Open Weight | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 1.05M |
| Overall Score | 54.6 | 72.14 |
| Benchmarks Covered | 11 | 48 |
| Pricing (input/output) | $0.95 / $4.00 | $3.00 / $15.00 |

## Category Breakdown

### Agentic

- Winner: Kimi K3
- Kimi K2.7 Code public-lane score: 37.6 (Supported · #64/119)
- Kimi K3 public-lane score: 68.1 (Supported · #8/119)

| Benchmark | Kimi K2.7 Code | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| Kimi Claw 24/7 | 46.9% | Coming soon | Coming soon |
| MCP Atlas | 76% | 84.2% | Kimi K3 |
| MCP Mark Verified | 81.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 67.0% | 80.9% | Kimi K3 |
| Terminal-Bench 2.1 | Coming soon | 88.3% | Coming soon |
| BrowseComp | Coming soon | 91.2% | Coming soon |
| DeepSearchQA | Coming soon | 95.0% | Coming soon |
| Toolathlon-Verified | Coming soon | 73.2% | Coming soon |
| AutomationBench | Coming soon | 30.8% | Coming soon |
| JobBench | Coming soon | 52.9% | Coming soon |
| APEX-Agents | Coming soon | 37.6% | Coming soon |
| SpreadsheetBench 2 | Coming soon | 34.8% | Coming soon |
| DECK-Bench | Coming soon | 73.5% | Coming soon |
| ApprenticeBench | Coming soon | 18% | Coming soon |

### Coding

- Winner: Kimi K3
- Kimi K2.7 Code public-lane score: 44.5 (Supported · #55/144)
- Kimi K3 public-lane score: 61.4 (Supported · #18/144)

| Benchmark | Kimi K2.7 Code | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| Kimi Code Bench v2 | 62.0% | 72.9% | Kimi K3 |
| ProgramBench | 53.6% | 77.8% | Kimi K3 |
| MLS-Bench Lite | 35.1% | 48.3% | Kimi K3 |
| CursorBench 3.2 | 49.7% | 60.8% | Kimi K3 |
| OpenHarmony Bench | 52.1% | 57.3% | Kimi K3 |
| LiveCodeBench (Vals) | 82.1% | 87.2% | Kimi K3 |
| SWE-bench (Vals) | 78.2% | 93.4% | Kimi K3 |
| DeepSWE | Coming soon | 67.5% | Coming soon |
| FrontierSWE | Coming soon | 81.2% | Coming soon |
| sweMarathon | Coming soon | 42% | Coming soon |
| PostTrain Bench | Coming soon | 36.6% | Coming soon |
| VulcanBench v3 | Coming soon | 73.7% | Coming soon |
| FrontierSWE v2 | Coming soon | 25.9% | Coming soon |
| PostTrainBench v1.1 | Coming soon | 32.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Kimi K2.7 Code public-lane score: 76.8 (Unranked · 2 rankable rows)
- Kimi K3 public-lane score: 65.8 (#18/27)

| Benchmark | Kimi K2.7 Code | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | Coming soon | 94.50% | Coming soon |
| ARC-AGI-2 | Coming soon | 60.4% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Kimi K2.7 Code public-lane score: Coming soon
- Kimi K3 public-lane score: 89.4 (#1/49)

| Benchmark | Kimi K2.7 Code | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | Coming soon | 63.3% | Coming soon |
| MMMU-Pro | Coming soon | 81.6% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 83.4% | Coming soon |
| CharXiv w/o tools | Coming soon | 84.8% | Coming soon |
| CharXiv | Coming soon | 91.3% | Coming soon |
| MathVision | Coming soon | 94.3% | Coming soon |
| MathVision w/ Python | Coming soon | 97.8% | Coming soon |
| BabyVision w/ Python | Coming soon | 85.7% | Coming soon |
| ZeroBench | Coming soon | 23.0% | Coming soon |
| ZeroBench w/ Python | Coming soon | 41.0% | Coming soon |
| WorldVQA ForceAnswer | Coming soon | 51.0% | Coming soon |
| OmniDocBench | Coming soon | 91.1% | Coming soon |
| PerceptionBench | Coming soon | 58.5% | Coming soon |

### Knowledge

- Winner: Directional only
- Kimi K2.7 Code public-lane score: 54.1 (Estimated · #53/171)
- Kimi K3 public-lane score: 67.9 (Supported · #18/171)

| Benchmark | Kimi K2.7 Code | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | Coming soon | 93.5% | Coming soon |
| GPQA-D | Coming soon | 93.5% | Coming soon |
| HLE | Coming soon | 56% | Coming soon |
| HLE w/o tools | Coming soon | 43.5% | 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 K2.7 Code public-lane score: 75.1 (#59/125)
- Kimi K3 public-lane score: Coming soon

| Benchmark | Kimi K2.7 Code | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | Coming soon | 52.7% | Coming soon |

## FAQ

### Which is better overall, Kimi K2.7 Code or Kimi K3?

Kimi K3 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Kimi K2.7 Code and Kimi K3?

The widest category gap is in agentic, where the averages are 37.6 for Kimi K2.7 Code and 68.1 for Kimi K3.

### How many benchmarks does Kimi K2.7 Code cover on BenchLM?

Kimi K2.7 Code currently has 11 sourced benchmark scores on BenchLM.

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

Kimi K3 currently has 48 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Kimi K2.7 Code vs GPT-6 Astra](/compare/gpt-6-astra-vs-kimi-k2-7-code)
- [Kimi K3 vs GPT-6 Astra](/compare/gpt-6-astra-vs-kimi-k3)
- [Kimi K2.7 Code vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k2-7-code)
- [Kimi K3 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k3)

## Explore More

- [Kimi K2.7 Code profile](/models/kimi-k2-7-code)
- [Kimi K3 profile](/models/kimi-k3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)