Model comparison
GPT-4o mini vs GPT-6 Luna
GPT-6 Luna is the stronger model overall, scoring 45.1 to 25.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and GPT-6 Luna in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Luna leads 54.7 to 21.6.
- 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.
Side by side
| GPT-4o mini | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 25.4 | 45.1 |
| Released | 2024-07-18 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 16K | 128K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.60 | $0.50 |
| Results tracked | 60 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-4o mini: 21.6 (#330), GPT-6 Luna: 54.7 (#24)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Coding | 1290 | 1448 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1583 |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.2 (#95), GPT-6 Luna: —
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning GPT-6 Luna leads
GPT-4o mini: 8.7 (#343), GPT-6 Luna: 31.7 (#68)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1415 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 68.7% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math GPT-6 Luna leads
GPT-4o mini: 9.9 (#307), GPT-6 Luna: 35.6 (#140)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Math | 1267 | 1396 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge GPT-6 Luna leads
GPT-4o mini: 17.7 (#279), GPT-6 Luna: 40.1 (#110)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Expert | 1235 | 1458 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal GPT-6 Luna leads
GPT-4o mini: 25.3 (#117), GPT-6 Luna: 42.0 (#27)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
| Furniture Assembly | — | 44.2% |
Multilingual GPT-6 Luna leads
GPT-4o mini: 42.2 (#194), GPT-6 Luna: 51.0 (#111)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1266 | 1390 |
| LMArena Chinese | 1264 | 1425 |
| LMArena Russian | 1275 | 1392 |
| LMArena Spanish | 1276 | 1416 |
| LMArena French | 1296 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1216 | — |
| LMArena Korean | 1195 | — |
Instruction Following GPT-6 Luna leads
GPT-4o mini: 62.1 (#234), GPT-6 Luna: 74.7 (#85)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1259 | 1414 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context GPT-6 Luna leads
GPT-4o mini: 39.1 (#181), GPT-6 Luna: 43.3 (#95)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1289 | 1417 |
Writing & Preference GPT-6 Luna leads
GPT-4o mini: 39.7 (#243), GPT-6 Luna: 58.4 (#115)
| Benchmark | GPT-4o mini | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1286 | 1392 |
| LMArena Creative Writing | 1268 | 1357 |
| LMArena Multi-Turn | 1285 | 1400 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than GPT-6 Luna?
GPT-6 Luna is the stronger model overall, scoring 45.1 to 25.4 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: 54.7 versus 21.6 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?
13 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and GPT-6 Luna has 18.