# Kimi K2.6 vs Mercury 2.5

> Side-by-side benchmark comparison for Kimi K2.6 and Mercury 2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-2-6-vs-mercury-2-5
- Last updated: September 8, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Kimi K2.6 and Mercury 2.5 share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Mercury 2.5 has the lower published output-token price.
- Mercury 2.5 has the larger published context window at 260K.

## Model Snapshot

| Property | Kimi K2.6 | Mercury 2.5 |
|----------|----------|----------|
| Creator | Moonshot AI | Inception |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 260K |
| Independent public score (not head-to-head) | 65.42 | null |
| Benchmarks Covered | 37 | 5 |
| Pricing (input/output) | $0.95 / $4.00 | $0.04 / $0.15 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 46.7 (Supported · #77/152)
- Mercury 2.5 public-lane score: 44.5 (Estimated · #91/152)

| Benchmark | Kimi K2.6 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 66.7% | Coming soon | Coming soon |
| BrowseComp | 83.2% | Coming soon | Coming soon |
| OSWorld-Verified | 73.1% | Coming soon | Coming soon |
| Toolathlon | 50% | Coming soon | Coming soon |
| MCP Atlas | 55.9% | Coming soon | Coming soon |
| Claw-Eval | 62.3% | Coming soon | Coming soon |
| DeepSearchQA | 92.5% | 34.0% | Kimi K2.6 |
| WideResearch | 80.8% | Coming soon | Coming soon |
| Gert Labs | 56.82% | Coming soon | Coming soon |
| ResearchClawBench | 18.0% | Coming soon | Coming soon |
| OSWorld 2.0 | 4.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 53.6% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 96.0% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 50.9 (Supported · #54/151)
- Mercury 2.5 public-lane score: 47.8 (Estimated · #73/151)

| Benchmark | Kimi K2.6 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | 89.6% | Coming soon | Coming soon |
| SWE-bench Pro | 58.6% | Coming soon | Coming soon |
| SWE Multilingual | 76.7% | Coming soon | Coming soon |
| SciCode | 52.2% | 38% | Kimi K2.6 |
| Terminal-Bench 2.0 | 66.7% | Coming soon | Coming soon |
| Vibe Code Bench | 37.89% | Coming soon | Coming soon |
| cursorBench31 | 47.6% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 86.8% | Coming soon | Coming soon |
| SWE-bench (Vals) | 76.2% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 64 (#26/48)
- Mercury 2.5 public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 79.4% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 80.1% | Coming soon | Coming soon |
| CharXiv | 80.4% | Coming soon | Coming soon |
| MathVision | 87.4% | Coming soon | Coming soon |
| V* | 96.9% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: Coming soon
- Mercury 2.5 public-lane score: 67.7 (Unranked · 1 rankable row)

### Knowledge

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 61.6 (Supported · #32/182)
- Mercury 2.5 public-lane score: 48.3 (Estimated · #94/182)

| Benchmark | Kimi K2.6 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 90.5% | Coming soon | Coming soon |
| GPQA-D | 90.5% | 79.0% | Kimi K2.6 |
| HLE | 34.7% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 89.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: Coming soon
- Mercury 2.5 public-lane score: 80.1 (#53/121)

| Benchmark | Kimi K2.6 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 77% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 71.3 (#1/7)
- Mercury 2.5 public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 96.4% | Coming soon | Coming soon |
| HMMT Feb 2026 | 92.7% | Coming soon | Coming soon |
| MMAnswerBench | 86.0% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 38.966% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 14.580% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Kimi K2.6 and Mercury 2.5?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Kimi K2.6 vs Mercury 2.5 Preview](/compare/kimi-2-6-vs-mercury-2-5-preview)
- [Mercury 2.5 vs Mercury 2.5 Preview](/compare/mercury-2-5-vs-mercury-2-5-preview)
- [Kimi K2.6 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-kimi-2-6)
- [Mercury 2.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-mercury-2-5)

## Explore More

- [Kimi K2.6 profile](/models/kimi-2-6)
- [Mercury 2.5 profile](/models/mercury-2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)