# GPT-4o mini vs GPT-6 Luna

> GPT-6 Luna is the stronger model overall, scoring 53.3 to 25.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4o-mini-vs-gpt-6-luna
- Last updated: 2026-10-12
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and GPT-6 Luna in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 98.9% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.15 / $0.60 for GPT-4o mini.
- GPT-6 Luna accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 25.5 | 53.3 |
| Rank | 343 | 36 |
| Context | 128K | 1.05M |
| Input $/M | $0.15 | $0.10 |
| Output $/M | $0.60 | $0.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4o mini: 22.0 (#335)
- GPT-6 Luna: 55.5 (#25)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Coding | 1290 | 1439 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1581 |
| SciCode | — | 54.6% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,577 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o mini: 27.5 (#101)
- GPT-6 Luna: 33.3 (#54)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| APEX-Agents | — | 44.3% |
| BALROG | 17.4% | — |
| GDP.pdf | — | 23% |

## Reasoning

- GPT-4o mini: 8.7 (#347)
- GPT-6 Luna: 48.2 (#41)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| ARC-AGI-2 | 0% | 59.3% |
| Chess Puzzles | 0% | 31% |
| LMArena Hard Prompts | 1267 | 1411 |
| Mystery Game Puzzles | 12% | 7% |
| DTBench | 54.4% | 90.1% |
| LMCA | 10.4% | 44.5% |
| Epoch Capabilities Index | 126.56 | 156.28 |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 68.7% |
| ARC-AGI-1 | — | 86.7% |
| CritPt | — | 19.4% |
| LiveBench Reasoning | 32.8% | — |
| LiveBench Data Analysis | 50% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |

## Math

- GPT-4o mini: 10.4 (#314)
- GPT-6 Luna: 76.1 (#15)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 78.9% |
| OTIS Mock AIME 2024-2025 | 6.9% | 98.9% |
| LMArena Math | 1267 | 1416 |
| FrontierMath Tier 4 | — | 56.1% |
| ProofBench | — | 64% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |

## Knowledge

- GPT-4o mini: 17.7 (#284)
- GPT-6 Luna: 57.0 (#41)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 37.7% | 90.5% |
| SimpleQA Verified | 8.3% | 41.4% |
| LMArena Expert | 1235 | 1444 |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |

## Multimodal

- GPT-4o mini: 25.9 (#122)
- GPT-6 Luna: 42.4 (#30)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1066 | 1217 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |

## Multilingual

- GPT-4o mini: 42.0 (#199)
- GPT-6 Luna: 50.5 (#117)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1266 | 1386 |
| LMArena Chinese | 1265 | 1433 |
| LMArena French | 1297 | 1420 |
| LMArena German | 1272 | 1369 |
| LMArena Japanese | 1216 | 1369 |
| LMArena Korean | 1195 | 1360 |
| LMArena Russian | 1275 | 1394 |
| LMArena Spanish | 1276 | 1393 |

## Instruction Following

- GPT-4o mini: 61.9 (#239)
- GPT-6 Luna: 74.3 (#99)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1258 | 1409 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |

## Long Context

- GPT-4o mini: 39.1 (#186)
- GPT-6 Luna: 43.0 (#111)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1289 | 1409 |

## Writing & Preference

- GPT-4o mini: 39.5 (#248)
- GPT-6 Luna: 58.3 (#119)

| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1286 | 1391 |
| LMArena Creative Writing | 1268 | 1363 |
| LMArena Multi-Turn | 1285 | 1396 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |

## FAQ

### Is GPT-4o mini better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 25.5 on the Noometry Index.

### Which is cheaper, GPT-4o mini or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GPT-4o mini lists at $0.15 and $0.60.

### Is GPT-4o mini or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 22.0 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 128K.

### How many benchmarks do GPT-4o mini and GPT-6 Luna share?

28 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and GPT-6 Luna has 42.