# Kimi K2.5 vs Qwen3.6-35B-A3B

> Side-by-side benchmark comparison for Kimi K2.5 and Qwen3.6-35B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-k2-5-vs-qwen3-6-35b-a3b
- Last updated: October 14, 2026

- Shared sourced benchmarks: 38
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Kimi K2.5 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Kimi K2.5 has the higher overall point estimate 52.79 to 43.54. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in mathematics, where the averages are 83.3 for Kimi K2.5 and 58.4 for Qwen3.6-35B-A3B.
- The biggest single benchmark swing is MCP Atlas in Agentic, with scores of 29.5% and 62.8%.
- Qwen3.6-35B-A3B also has the larger context window at 262K.

## Model Snapshot

| Property | Kimi K2.5 | Qwen3.6-35B-A3B |
|----------|----------|----------|
| Creator | Moonshot AI | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 256K | 262K |
| Overall Score | 52.79 | 43.54 |
| Benchmarks Covered | 68 | 42 |
| Pricing (input/output) | $0.60 / $3.00 | N/A |

## Category Breakdown

### Agentic

- Winner: Directional only
- Kimi K2.5 public-lane score: 40.1 (Estimated · #62/124)
- Qwen3.6-35B-A3B public-lane score: 29.2 (Estimated · #90/124)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 50.8% | 51.5% | Qwen3.6-35B-A3B |
| BrowseComp | 60.6% | Coming soon | Coming soon |
| OSWorld-Verified | 63.3% | Coming soon | Coming soon |
| Claw-Eval | 52.3% | 68.7% | Qwen3.6-35B-A3B |
| QwenClawBench | 54.3% | 52.6% | Kimi K2.5 |
| τ³-bench results | 65.7% | 67.2% | Qwen3.6-35B-A3B |
| DeepSearchQA | 77.1% | Coming soon | Coming soon |
| DeepPlanning | 14.4% | 25.9% | Qwen3.6-35B-A3B |
| Toolathlon | 27.8% | 26.9% | Kimi K2.5 |
| MCP Atlas | 29.5% | 62.8% | Qwen3.6-35B-A3B |
| MCP-Tasks | 59.1% | Coming soon | Coming soon |
| WideResearch | 72.7% | 60.1% | Kimi K2.5 |
| BFCL v4 | 68.3% | Coming soon | Coming soon |
| Gert Labs | 45.88% | 42.65% | Kimi K2.5 |
| ResearchClawBench | 14.0% | Coming soon | Coming soon |
| JobBench | 8.7% | Coming soon | Coming soon |
| QwenWebBench | Coming soon | 1397 | Coming soon |
| VITA-Bench | Coming soon | 35.6% | Coming soon |

### Coding

- Winner: Directional only
- Kimi K2.5 public-lane score: 38.9 (Estimated · #66/149)
- Qwen3.6-35B-A3B public-lane score: 31.8 (Estimated · #89/149)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.8% | 73.4% | Kimi K2.5 |
| SWE-bench Verified* | 70.8% | Coming soon | Coming soon |
| LiveCodeBench v6 | 85.0% | 80.4% | Kimi K2.5 |
| SWE-bench Pro | 50.7% | 49.5% | Kimi K2.5 |
| SWE Multilingual | 73% | 67.2% | Kimi K2.5 |
| SWE-Rebench | 58.5% | Coming soon | Coming soon |
| React Native Evals | 77.2% | Coming soon | Coming soon |
| NL2Repo | 32% | 29.4% | Kimi K2.5 |
| SciCode | 48.7% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 50.8% | 51.5% | Qwen3.6-35B-A3B |

### Reasoning

- Winner: Not comparable
- Kimi K2.5 public-lane score: 72.2 (Unranked · 3 rankable rows)
- Qwen3.6-35B-A3B public-lane score: 75.1 (Unranked · 2 rankable rows)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 61% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Kimi K2.5
- Kimi K2.5 public-lane score: 70.4 (#32/54)
- Qwen3.6-35B-A3B public-lane score: 66.4 (#40/54)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 84.3% | 81.7% | Kimi K2.5 |
| MMMU-Pro | 78.5% | 75.3% | Kimi K2.5 |
| RealWorldQA | 81.0% | 85.3% | Qwen3.6-35B-A3B |
| OmniDocBench 1.5 | 88.8% | 89.9% | Qwen3.6-35B-A3B |
| Video-MME | 87.4% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 87.4% | 86.6% | Kimi K2.5 |
| Video-MME (w/o subtitle) | 83.2% | 82.5% | Kimi K2.5 |
| MathVision | 84.2% | Coming soon | Coming soon |
| We-Math | 84.7% | Coming soon | Coming soon |
| DynaMath | 84.4% | Coming soon | Coming soon |
| SimpleVQA | 71.2% | 58.9% | Kimi K2.5 |
| MMLongBench-Doc | 58.5% | Coming soon | Coming soon |
| CC-OCR | 79.7% | 81.9% | Qwen3.6-35B-A3B |
| AI2D_TEST | 90.8% | 92.7% | Qwen3.6-35B-A3B |
| CountBench | 94.1% | Coming soon | Coming soon |
| RefCOCO (avg) | 87.8% | 92.0% | Qwen3.6-35B-A3B |
| MMVU | 80.4% | Coming soon | Coming soon |
| VideoMMMU | 86.6% | 83.7% | Kimi K2.5 |
| MLVU (M-Avg) | 85.0% | 86.2% | Qwen3.6-35B-A3B |
| CharXiv | 77.5% | 78% | Qwen3.6-35B-A3B |
| ODINW13 | Coming soon | 50.8% | Coming soon |

### Knowledge

- Winner: Directional only
- Kimi K2.5 public-lane score: 51.5 (Estimated · #72/181)
- Qwen3.6-35B-A3B public-lane score: 42.9 (Estimated · #105/181)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.6% | 86% | Kimi K2.5 |
| GPQA-D | 87.6% | Coming soon | Coming soon |
| SuperGPQA | 69.2% | 64.7% | Kimi K2.5 |
| MMLU-Pro | 87.1% | 85.2% | Kimi K2.5 |
| MMLU-Pro (Arcee) | 87.1% | Coming soon | Coming soon |
| MMLU-Redux | 94.5% | Coming soon | Coming soon |
| C-Eval | 94% | 90% | Kimi K2.5 |
| HLE | 30.1% | 21.4% | Kimi K2.5 |

### Multilingual

- Winner: Not comparable
- Kimi K2.5 public-lane score: 87.3 (#8/17)
- Qwen3.6-35B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 82.3% | Coming soon | Coming soon |
| NOVA-63 | 56.0% | Coming soon | Coming soon |
| INCLUDE | 83.3% | Coming soon | Coming soon |
| PolyMath | 43.1% | Coming soon | Coming soon |
| MAXIFE | 72.8% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- Kimi K2.5 public-lane score: 85.8 (#46/128)
- Qwen3.6-35B-A3B public-lane score: 78.3 (#58/128)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 93.9% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Kimi K2.5 public-lane score: 83.3 (Unranked · 7 rankable rows)
- Qwen3.6-35B-A3B public-lane score: 58.4 (#10/12)

| Benchmark | Kimi K2.5 | Qwen3.6-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 96.1% | Coming soon | Coming soon |
| AIME26 | 95.8% | 92.7% | Kimi K2.5 |
| AIME25 (Arcee) | 96.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 95.4% | 90.7% | Kimi K2.5 |
| HMMT Nov 2025 | 91.1% | 89.1% | Kimi K2.5 |
| HMMT Feb 2026 | 87.1% | 83.6% | Kimi K2.5 |
| MMAnswerBench | 81.8% | 78.9% | Kimi K2.5 |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 20.351% | Coming soon |

## FAQ

### Which is better overall, Kimi K2.5 or Qwen3.6-35B-A3B?

Kimi K2.5 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Kimi K2.5 and Qwen3.6-35B-A3B?

The widest category gap is in mathematics, where the averages are 83.3 for Kimi K2.5 and 58.4 for Qwen3.6-35B-A3B.

### How many benchmarks does Kimi K2.5 cover on BenchLM?

Kimi K2.5 currently has 68 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.6-35B-A3B cover on BenchLM?

Qwen3.6-35B-A3B currently has 42 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Kimi K2.5 vs Kimi K2.5 (Reasoning)](/compare/kimi-k2-5-vs-kimi-k2-5-reasoning)
- [Qwen3.6-35B-A3B vs Kimi K2.5 (Reasoning)](/compare/kimi-k2-5-reasoning-vs-qwen3-6-35b-a3b)
- [Kimi K2.5 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k2-5)
- [Qwen3.6-35B-A3B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-6-35b-a3b)

## Explore More

- [Kimi K2.5 profile](/models/kimi-k2-5)
- [Qwen3.6-35B-A3B profile](/models/qwen3-6-35b-a3b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)