Model comparison
GPT-5.6 Luna vs Mixtral 8x22B
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 26.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GPT-5.6 Luna scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 21.2.
- The biggest single-benchmark swing is WeirdML: 60.9% for GPT-5.6 Luna and 3.2% for Mixtral 8x22B.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Mixtral 8x22B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.7 | 26.7 |
| Released | 2026-07-09 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 64K |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $1.20 | $6 |
| Results tracked | 51 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 53.9 (#25), Mixtral 8x22B: 23.8 (#324)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| WeirdML | 60.9% | 3.2% |
| LMArena Coding | 1466 | 1166 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1517 | — |
| SciCode | 53.6% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 1,667 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use GPT-5.6 Luna leads
GPT-5.6 Luna: 35.3 (#37), Mixtral 8x22B: 22.8 (#119)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.5 (#38), Mixtral 8x22B: 19.1 (#246)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1150 |
| DTBench | 89.1% | 55.1% |
| Epoch Capabilities Index | 156.32 | 122 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| ForecastBench | — | 56.3 |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.5 (#12), Mixtral 8x22B: 21.2 (#271)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1455 | 1184 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.6 (#31), Mixtral 8x22B: 15.1 (#288)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 91.6% | 34.1% |
| LMArena Expert | 1479 | 1113 |
| SimpleQA Verified | 41% | — |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multimodal Not comparable
GPT-5.6 Luna: 43.0 (#22), Mixtral 8x22B: —
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1259 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 53.0 (#73), Mixtral 8x22B: 32.9 (#250)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1418 | 1128 |
| LMArena Chinese | 1469 | 1116 |
| LMArena French | 1457 | 1165 |
| LMArena German | 1459 | 1141 |
| LMArena Japanese | 1416 | 1037 |
| LMArena Korean | 1414 | 1056 |
| LMArena Russian | 1428 | 1158 |
| LMArena Spanish | 1445 | 1150 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 76.0 (#48), Mixtral 8x22B: 57.9 (#261)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1440 | 1147 |
| IFEval | — | 72.4% |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#78), Mixtral 8x22B: 34.6 (#242)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1437 | 1144 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.3 (#27), Mixtral 8x22B: 37.1 (#257)
| Benchmark | GPT-5.6 Luna | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1432 | 1162 |
| LMArena Creative Writing | 1397 | 1141 |
| LMArena Multi-Turn | 1433 | 1130 |
| EQ-Bench Creative Writing | 1829 | — |
| WildBench | — | 71.1% |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Mixtral 8x22B?
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 26.7 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Mixtral 8x22B?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is GPT-5.6 Luna or Mixtral 8x22B better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 64K.
How many benchmarks do GPT-5.6 Luna and Mixtral 8x22B share?
21 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Mixtral 8x22B has 34.