# GPT-5.4 mini vs GPT-6 Luna

> Side-by-side benchmark comparison for GPT-5.4 mini and GPT-6 Luna across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-4-mini-vs-gpt-6-luna
- Last updated: September 22, 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 GPT-5.4 mini and GPT-6 Luna.

## Summary

- GPT-5.4 mini and GPT-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 | GPT-5.4 mini | GPT-6 Luna |
|----------|----------|----------|
| Creator | OpenAI | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 400K | 1.05M |
| Independent public score (not head-to-head) | 61.31 | 62.33 |
| Benchmarks Covered | 19 | 7 |
| Pricing (input/output) | $0.75 / $4.50 | $0.10 / $0.50 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 39.5 (Supported · #124/157)
- GPT-6 Luna public-lane score: 56.7 (Estimated · #35/157)

| Benchmark | GPT-5.4 mini | GPT-6 Luna | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 60% | Coming soon | Coming soon |
| OSWorld-Verified | 72.1% | Coming soon | Coming soon |
| MCP Atlas | 57.7% | Coming soon | Coming soon |
| Toolathlon | 42.9% | Coming soon | Coming soon |
| τ²-bench results | 93.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 54.7% | Coming soon | Coming soon |
| ExploitGym | Coming soon | 11.6% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 43 (Supported · #111/159)
- GPT-6 Luna public-lane score: 66.6 (Estimated · #11/159)

| Benchmark | GPT-5.4 mini | GPT-6 Luna | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 47.97% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 27.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 81.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 73.0% | Coming soon | Coming soon |
| DeepSWE | Coming soon | 66.6% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 73.9 (Unranked · 2 rankable rows)
- GPT-6 Luna public-lane score: 78.3 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 57.3 (#33/50)
- GPT-6 Luna public-lane score: 71.3 (Unranked · 1 rankable row)

| Benchmark | GPT-5.4 mini | GPT-6 Luna | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 76.6% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 78% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 55.5 (Supported · #55/189)
- GPT-6 Luna public-lane score: 63.6 (Estimated · #29/189)

| Benchmark | GPT-5.4 mini | GPT-6 Luna | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 88% | Coming soon | Coming soon |
| HLE | 41.5% | Coming soon | Coming soon |
| HLE w/o tools | 28.2% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 83.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 84.6% | Coming soon | Coming soon |
| HealthBench (raw) | Coming soon | 50.0% | Coming soon |
| HealthBench (length-adjusted) | Coming soon | 54.5% | Coming soon |
| HealthBench Professional | Coming soon | 60.8% | Coming soon |
| HealthBench Professional (raw) | Coming soon | 61.2% | Coming soon |
| HealthBench Hard | Coming soon | 31.4% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 88.5 (#24/124)
- GPT-6 Luna public-lane score: Coming soon

### Mathematics

- Winner: Insufficient shared evidence
- GPT-5.4 mini public-lane score: 44.3 (Unranked · 2 rankable rows)
- GPT-6 Luna public-lane score: Coming soon

| Benchmark | GPT-5.4 mini | GPT-6 Luna | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 28.280% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.080% | Coming soon | Coming soon |

## FAQ

### Can I compare GPT-5.4 mini and GPT-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

- [GPT-5.4 mini vs GPT-5.4](/compare/gpt-5-4-vs-gpt-5-4-mini)
- [GPT-6 Luna vs GPT-5.4](/compare/gpt-5-4-vs-gpt-6-luna)
- [GPT-5.4 mini vs GPT-5.4 Pro](/compare/gpt-5-4-mini-vs-gpt-5-4-pro)
- [GPT-6 Luna vs GPT-5.4 Pro](/compare/gpt-5-4-pro-vs-gpt-6-luna)

## Explore More

- [GPT-5.4 mini profile](/models/gpt-5-4-mini)
- [GPT-6 Luna profile](/models/gpt-6-luna)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)