# GPT-5.6 Luna vs Kimi K2.5

> Side-by-side benchmark comparison for GPT-5.6 Luna and Kimi K2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-6-luna-vs-kimi-k2-5
- Last updated: September 24, 2026

- Shared sourced benchmarks: 8
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick GPT-5.6 Luna if you want the stronger benchmark profile. Kimi K2.5 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- GPT-5.6 Luna leads overall 65.6 to 52.96.
- The clearest category separation is in mathematics, where the averages are 94.2 for GPT-5.6 Luna and 62.1 for Kimi K2.5.
- The biggest single benchmark swing is FrontierMath v2 (Tier 4) in Mathematics, with scores of 58.500% and 4.200%.
- GPT-5.6 Luna is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.6 Luna also has the larger context window at 1.05M.

## Model Snapshot

| Property | GPT-5.6 Luna | Kimi K2.5 |
|----------|----------|----------|
| Creator | OpenAI | Moonshot AI |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 1.05M | 256K |
| Overall Score | 65.6 | 52.96 |
| Benchmarks Covered | 29 | 45 |
| Pricing (input/output) | $0.20 / $1.20 | $0.60 / $3.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- GPT-5.6 Luna public-lane score: 55.3 (Supported · #28/105)
- Kimi K2.5 public-lane score: 36.1 (Estimated · #52/105)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 14.3% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 84.7% | Coming soon | Coming soon |
| BrowseComp | 83.3% | 60.6% | GPT-5.6 Luna |
| OSWorld 2.0 | 45.6% | Coming soon | Coming soon |
| CyberGym | 77.9% | Coming soon | Coming soon |
| ExploitGym | 12.4% | Coming soon | Coming soon |
| Toolathlon | 53.4% | 27.8% | GPT-5.6 Luna |
| Terminal-Bench 2.1 (Vals) | 79.0% | Coming soon | Coming soon |
| ApprenticeBench | 7% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 50.8% | Coming soon |
| Claw-Eval | Coming soon | 52.3% | Coming soon |
| QwenClawBench | Coming soon | 54.3% | Coming soon |
| τ³-bench results | Coming soon | 65.7% | Coming soon |
| DeepSearchQA | Coming soon | 77.1% | Coming soon |
| DeepPlanning | Coming soon | 14.4% | Coming soon |
| MCP Atlas | Coming soon | 29.5% | Coming soon |
| MCP-Tasks | Coming soon | 59.1% | Coming soon |
| WideResearch | Coming soon | 72.7% | Coming soon |
| Gert Labs | Coming soon | 45.88% | Coming soon |
| ResearchClawBench | Coming soon | 14.0% | Coming soon |
| JobBench | Coming soon | 8.7% | Coming soon |

### Coding

- Winner: Directional only
- GPT-5.6 Luna public-lane score: 64.5 (Supported · #9/135)
- Kimi K2.5 public-lane score: 38.9 (Estimated · #61/135)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 62.7% | 50.7% | GPT-5.6 Luna |
| Terminal-Bench 2.1 | 84.7% | Coming soon | Coming soon |
| DeepSWE | 67.2% | Coming soon | Coming soon |
| FrontierCode 1.1 Extended | 55.1% | Coming soon | Coming soon |
| cursorBench32 | 61.1% | Coming soon | Coming soon |
| VulcanBench v3 | 85.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 93.0% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 76.8% | Coming soon |
| SWE-bench Verified* | Coming soon | 70.8% | Coming soon |
| LiveCodeBench v6 | Coming soon | 85.0% | Coming soon |
| SWE Multilingual | Coming soon | 73% | Coming soon |
| SWE-Rebench | Coming soon | 58.5% | Coming soon |
| React Native Evals | Coming soon | 77.2% | Coming soon |
| SciCode | Coming soon | 48.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 54.7 (#18/19)
- Kimi K2.5 public-lane score: 55.1 (Unranked · 3 rankable rows)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 59.5% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.2% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 61% | Coming soon |

### Multimodal & Grounded

- Winner: GPT-5.6 Luna
- GPT-5.6 Luna public-lane score: 67.1 (#22/50)
- Kimi K2.5 public-lane score: 65.8 (#25/50)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 78.4% | 78.5% | Kimi K2.5 |
| MMMU-Pro w/ Python | 79.5% | Coming soon | Coming soon |
| Video-MME | Coming soon | 87.4% | Coming soon |
| MMVU | Coming soon | 80.4% | Coming soon |
| VideoMMMU | Coming soon | 86.6% | Coming soon |

### Knowledge

- Winner: Directional only
- GPT-5.6 Luna public-lane score: 64.6 (Supported · #22/158)
- Kimi K2.5 public-lane score: 47.8 (Estimated · #65/158)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.3% | 87.6% | GPT-5.6 Luna |
| GPQA-D | 92.3% | 87.6% | GPT-5.6 Luna |
| HealthBench Professional | 55.7% | Coming soon | Coming soon |
| HealthBench Hard | 32.0% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 91.7% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.0% | Coming soon | Coming soon |
| SuperGPQA | Coming soon | 69.2% | Coming soon |
| MMLU-Pro | Coming soon | 87.1% | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 87.1% | Coming soon |
| HLE | Coming soon | 30.1% | Coming soon |

### Multilingual

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: Coming soon
- Kimi K2.5 public-lane score: 38.2 (#8/12)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 82.3% | Coming soon |
| NOVA-63 | Coming soon | 56.0% | Coming soon |

### Instruction Following

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: Coming soon
- Kimi K2.5 public-lane score: 84.4 (#41/124)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 93.9% | Coming soon |

### Mathematics

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 94.2 (Unranked · 3 rankable rows)
- Kimi K2.5 public-lane score: 62.1 (#4/7)

| Benchmark | GPT-5.6 Luna | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath (legacy) | 78.6% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 78.600% | 27.900% | GPT-5.6 Luna |
| FrontierMath v2 (Tier 4) | 58.500% | 4.200% | GPT-5.6 Luna |
| AIME 2025 | Coming soon | 96.1% | Coming soon |
| AIME26 | Coming soon | 95.8% | Coming soon |
| AIME25 (Arcee) | Coming soon | 96.3% | Coming soon |
| HMMT Feb 2025 | Coming soon | 95.4% | Coming soon |
| HMMT Nov 2025 | Coming soon | 91.1% | Coming soon |
| HMMT Feb 2026 | Coming soon | 87.1% | Coming soon |
| MMAnswerBench | Coming soon | 81.8% | Coming soon |

## FAQ

### Which is better overall, GPT-5.6 Luna or Kimi K2.5?

GPT-5.6 Luna is ahead overall on BenchLM right now.

### Where is the biggest gap between GPT-5.6 Luna and Kimi K2.5?

The widest category gap is in mathematics, where the averages are 94.2 for GPT-5.6 Luna and 62.1 for Kimi K2.5.

### How many benchmarks does GPT-5.6 Luna cover on BenchLM?

GPT-5.6 Luna currently has 29 sourced benchmark scores on BenchLM.

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

Kimi K2.5 currently has 45 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5.6 Luna vs GPT-5.6 Sol](/compare/gpt-5-6-luna-vs-gpt-5-6-sol)
- [Kimi K2.5 vs GPT-5.6 Sol](/compare/gpt-5-6-sol-vs-kimi-k2-5)
- [GPT-5.6 Luna vs GPT-5.6 Terra](/compare/gpt-5-6-luna-vs-gpt-5-6-terra)
- [Kimi K2.5 vs GPT-5.6 Terra](/compare/gpt-5-6-terra-vs-kimi-k2-5)

## Explore More

- [GPT-5.6 Luna profile](/models/gpt-5-6-luna)
- [Kimi K2.5 profile](/models/kimi-k2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)