# BTL-3 vs GPT-5.6 Luna

> Side-by-side benchmark comparison for BTL-3 and GPT-5.6 Luna across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/btl-3-vs-gpt-5-6-luna
- Last updated: September 10, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for BTL-3 and GPT-5.6 Luna.

## Summary

- BTL-3 and GPT-5.6 Luna do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | BTL-3 | GPT-5.6 Luna |
|----------|----------|----------|
| Creator | Bad Theory Labs | OpenAI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 1.05M |
| Independent public score (not head-to-head) | null | 64.65 |
| Benchmarks Covered | 3 | 28 |
| Pricing (input/output) | $0.00 / $0.00 | $1.00 / $6.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- BTL-3 public-lane score: Coming soon
- GPT-5.6 Luna public-lane score: 56.8 (Supported · #32/152)

| Benchmark | BTL-3 | GPT-5.6 Luna | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | 88.5% | Coming soon | Coming soon |
| Terminal-Bench 3.0 | Coming soon | 14.3% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 84.7% | Coming soon |
| BrowseComp | Coming soon | 83.3% | Coming soon |
| OSWorld 2.0 | Coming soon | 45.6% | Coming soon |
| CyberGym | Coming soon | 77.9% | Coming soon |
| ExploitGym | Coming soon | 12.4% | Coming soon |
| Toolathlon | Coming soon | 53.4% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 79.0% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- BTL-3 public-lane score: Coming soon
- GPT-5.6 Luna public-lane score: 66.8 (Supported · #9/151)

| Benchmark | BTL-3 | GPT-5.6 Luna | Winner |
|-----------|-----------|-----------|--------|
| HumanEval | 95.1% | Coming soon | Coming soon |
| LiveCodeBench v6 | 88.1% | Coming soon | Coming soon |
| SWE-bench Pro | Coming soon | 62.7% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 84.7% | Coming soon |
| DeepSWE | Coming soon | 67.2% | Coming soon |
| FrontierCode 1.1 Extended | Coming soon | 55.1% | Coming soon |
| cursorBench32 | Coming soon | 61.1% | Coming soon |
| VulcanBench v3 | Coming soon | 85.5% | Coming soon |
| SWE-bench (Vals) | Coming soon | 93.0% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- BTL-3 public-lane score: Coming soon
- GPT-5.6 Luna public-lane score: 67.1 (#21/48)

| Benchmark | BTL-3 | GPT-5.6 Luna | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 78.4% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 79.5% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- BTL-3 public-lane score: Coming soon
- GPT-5.6 Luna public-lane score: 51.2 (#19/20)

| Benchmark | BTL-3 | GPT-5.6 Luna | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | Coming soon | 59.5% | Coming soon |
| ARC-AGI-3 | Coming soon | 0.2% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- BTL-3 public-lane score: Coming soon
- GPT-5.6 Luna public-lane score: 64.1 (Supported · #27/183)

| Benchmark | BTL-3 | GPT-5.6 Luna | Winner |
|-----------|-----------|-----------|--------|
| GPQA | Coming soon | 92.3% | Coming soon |
| GPQA-D | Coming soon | 92.3% | Coming soon |
| HealthBench Professional | Coming soon | 55.7% | Coming soon |
| HealthBench Hard | Coming soon | 32.0% | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 91.7% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 86.0% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- BTL-3 public-lane score: Coming soon
- GPT-5.6 Luna public-lane score: 94.4 (Unranked · 3 rankable rows)

| Benchmark | BTL-3 | GPT-5.6 Luna | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath (legacy) | Coming soon | 78.6% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 78.600% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 58.500% | Coming soon |

## FAQ

### Can I compare BTL-3 and GPT-5.6 Luna on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [BTL-3 vs BTL-4](/compare/btl-3-vs-btl-4)
- [GPT-5.6 Luna vs BTL-4](/compare/btl-4-vs-gpt-5-6-luna)
- [BTL-3 vs BTL-4 Compact](/compare/btl-3-vs-btl-4-compact)
- [GPT-5.6 Luna vs BTL-4 Compact](/compare/btl-4-compact-vs-gpt-5-6-luna)

## Explore More

- [BTL-3 profile](/models/btl-3)
- [GPT-5.6 Luna profile](/models/gpt-5-6-luna)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)