# GPT-5.6 Luna vs Inkling 2 Small

> Side-by-side benchmark comparison for GPT-5.6 Luna and Inkling 2 Small across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-6-luna-vs-inkling-2-small
- Last updated: November 7, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GPT-5.6 Luna leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GPT-5.6 Luna has the higher overall point estimate 64.03 to 59.06. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in reasoning, where the averages are 56.5 for GPT-5.6 Luna and 86.1 for Inkling 2 Small.
- The biggest single benchmark swing is BrowseComp in Agentic, with scores of 83.3% and 90.2%.
- Inkling 2 Small 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 | Inkling 2 Small |
|----------|----------|----------|
| Creator | OpenAI | Thinking Machines Lab |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Hybrid |
| Context | 1.05M | 1M |
| Overall Score | 64.03 | 59.06 |
| Benchmarks Covered | 34 | 25 |
| Pricing (input/output) | $0.20 / $1.20 | $0.30 / $1.00 |

## Category Breakdown

### Agentic

- Winner: Inkling 2 Small
- GPT-5.6 Luna public-lane score: 58.8 (Supported · #32/131)
- Inkling 2 Small public-lane score: 59.9 (Supported · #26/131)

| Benchmark | GPT-5.6 Luna | Inkling 2 Small | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 14.3% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 84.7% | 85.1% | Inkling 2 Small |
| BrowseComp | 83.3% | 90.2% | Inkling 2 Small |
| 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% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 79.0% | Coming soon | Coming soon |
| ApprenticeBench | 7% | Coming soon | Coming soon |
| MazeBench | 0% | Coming soon | Coming soon |
| DeepSearchQA | Coming soon | 90.9% | Coming soon |
| MCP Atlas | Coming soon | 85% | Coming soon |
| JobBench | Coming soon | 70.5% | Coming soon |

### Coding

- Winner: GPT-5.6 Luna
- GPT-5.6 Luna public-lane score: 61.9 (Supported · #17/157)
- Inkling 2 Small public-lane score: 59.7 (Supported · #20/157)

| Benchmark | GPT-5.6 Luna | Inkling 2 Small | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 62.7% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 84.7% | 85.1% | Inkling 2 Small |
| DeepSWE | 67.2% | 72.1% | Inkling 2 Small |
| FrontierCode 1.1 Extended | 55.1% | Coming soon | Coming soon |
| CursorBench 3.2 | 61.1% | Coming soon | Coming soon |
| VulcanBench v3 | 85.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 93.0% | Coming soon | Coming soon |
| CursorBench 4.0 | 35.9% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 82.2% | Coming soon |
| SWE Multilingual | Coming soon | 81.2% | Coming soon |
| sweMarathon | Coming soon | 38.8% | Coming soon |
| PostTrainBench v1.2 | Coming soon | 31.9% | Coming soon |

### Reasoning

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 56.5 (#24/25)
- Inkling 2 Small public-lane score: 86.1 (Unranked · 2 rankable rows)

| Benchmark | GPT-5.6 Luna | Inkling 2 Small | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 59.5% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.2% | Coming soon | Coming soon |
| ARC-AGI-1 | 88.00% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 70.6% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- GPT-5.6 Luna public-lane score: 78.9 (#23/59)
- Inkling 2 Small public-lane score: 86.6 (#12/59)

| Benchmark | GPT-5.6 Luna | Inkling 2 Small | Winner |
|-----------|-----------|-----------|--------|
| ExtractBench (LlamaIndex) | 91.16% | Coming soon | Coming soon |
| ParseBench | 66.86% | Coming soon | Coming soon |
| MMMU-Pro | 78.4% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 79.5% | Coming soon | Coming soon |
| CharXiv | Coming soon | 87.7% | Coming soon |
| CharXiv w/o tools | Coming soon | 85.6% | Coming soon |
| Chartography (no tools) | Coming soon | 36.7% | Coming soon |
| Chartography (tools) | Coming soon | 80.4% | Coming soon |
| BabyVision | Coming soon | 68.6% | Coming soon |
| BabyVision w/ Python | Coming soon | 93.7% | Coming soon |
| ScreenSpot Pro | Coming soon | 83.8% | Coming soon |
| PerceptionBench | Coming soon | 64.7% | Coming soon |
| MathVision | Coming soon | 92.8% | Coming soon |

### Knowledge

- Winner: Directional only
- GPT-5.6 Luna public-lane score: 63.7 (Supported · #39/178)
- Inkling 2 Small public-lane score: 60.4 (Estimated · #46/178)

| Benchmark | GPT-5.6 Luna | Inkling 2 Small | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.3% | 93% | Inkling 2 Small |
| GPQA-D | 92.3% | 93.0% | Inkling 2 Small |
| 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 |

### Mathematics

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 80.5 (Unranked · 3 rankable rows)
- Inkling 2 Small public-lane score: 85.9 (Unranked · 2 rankable rows)

| Benchmark | GPT-5.6 Luna | Inkling 2 Small | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath (legacy) | 78.6% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 78.600% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 58.500% | Coming soon | Coming soon |
| HMMT Feb 2026 | Coming soon | 95.8% | Coming soon |
| Apex | Coming soon | 63.5% | Coming soon |

## FAQ

### Which is better overall, GPT-5.6 Luna or Inkling 2 Small?

GPT-5.6 Luna has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GPT-5.6 Luna and Inkling 2 Small?

The widest category gap is in reasoning, where the averages are 56.5 for GPT-5.6 Luna and 86.1 for Inkling 2 Small.

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

GPT-5.6 Luna currently has 34 sourced benchmark scores on BenchLM.

### How many benchmarks does Inkling 2 Small cover on BenchLM?

Inkling 2 Small currently has 25 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)
- [Inkling 2 Small vs GPT-5.6 Sol](/compare/gpt-5-6-sol-vs-inkling-2-small)
- [GPT-5.6 Luna vs GPT-5.6 Terra](/compare/gpt-5-6-luna-vs-gpt-5-6-terra)
- [Inkling 2 Small vs GPT-5.6 Terra](/compare/gpt-5-6-terra-vs-inkling-2-small)

## Explore More

- [GPT-5.6 Luna profile](/models/gpt-5-6-luna)
- [Inkling 2 Small profile](/models/inkling-2-small)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)