Model comparison
GPT-6 Luna vs Wizardlm 70b
GPT-6 Luna is the stronger model overall, scoring 53.3 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
MicrosoftSummary
- They share 12 benchmarks with published results for both. GPT-6 Luna scores higher in 7 categories and Wizardlm 70b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 32.2.
- Wizardlm 70b has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Wizardlm 70b | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 53.3 | 33.0 |
| Released | 2026-09-22 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 42 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 55.5 (#25), Wizardlm 70b: 31.4 (#285)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1439 | 1081 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1581 | — |
| SciCode | 54.6% | — |
| ALE-Bench | 1,577 | — |
Agentic & Tool Use Not comparable
GPT-6 Luna: 33.3 (#54), Wizardlm 70b: —
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| APEX-Agents | 44.3% | — |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), Wizardlm 70b: 20.7 (#234)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1079 |
| ARC-AGI-2 | 59.3% | — |
| NYT Connections (extended) | 68.7% | — |
| ARC-AGI-1 | 86.7% | — |
| CritPt | 19.4% | — |
| Chess Puzzles | 31% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 90.1% | — |
| LMCA | 44.5% | — |
| Epoch Capabilities Index | 156.28 | — |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Wizardlm 70b: 32.2 (#218)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1416 | 1116 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 64% | — |
Knowledge Not comparable
GPT-6 Luna: 57.0 (#41), Wizardlm 70b: —
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
| LMArena Expert | 1444 | — |
Multimodal Not comparable
GPT-6 Luna: 42.4 (#30), Wizardlm 70b: —
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Vision | 1217 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 50.5 (#117), Wizardlm 70b: 29.6 (#265)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1386 | 1078 |
| LMArena Chinese | 1433 | 1052 |
| LMArena German | 1369 | 1083 |
| LMArena Russian | 1394 | 1155 |
| LMArena French | 1420 | — |
| LMArena Japanese | 1369 | — |
| LMArena Korean | 1360 | — |
| LMArena Spanish | 1393 | — |
Instruction Following GPT-6 Luna leads
GPT-6 Luna: 74.3 (#99), Wizardlm 70b: 56.3 (#273)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1409 | 1093 |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.0 (#111), Wizardlm 70b: 33.3 (#263)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1409 | 1097 |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.3 (#119), Wizardlm 70b: 34.8 (#269)
| Benchmark | GPT-6 Luna | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1391 | 1120 |
| LMArena Creative Writing | 1363 | 1149 |
| LMArena Multi-Turn | 1396 | 1108 |
Frequently asked questions
Is GPT-6 Luna better than Wizardlm 70b?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 33.0 on the Noometry Index.
Is GPT-6 Luna or Wizardlm 70b better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 31.4 in the Noometry coding category.
How many benchmarks do GPT-6 Luna and Wizardlm 70b share?
12 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Wizardlm 70b has 12.