Compare / head-to-head
GPT-6 Lunavs
Muse Spark 1.2
Muse Spark 1.2 leads 8 of 15 shared benchmarks. GPT-6 Luna is 9.2x cheaper per token. GPT-6 Luna has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
6 – 8
Muse Spark 1.2 leads · 1 tied
Cheaper per token
GPT-6 Luna
9.2x cheaper, input + output
Larger context
GPT-6 Luna
1.1M tokens
Providers
2 providers
OpenAI · Meta
GPT-6 Luna
OpenAI · released 2026-09-22
textvision
Muse Spark 1.2
Meta · released 2026-08-05
textvisionvideoaudio
Quality
Benchmark matrix
15 shared · 7 only GPT-6 Luna · 8 only Muse Spark 1.2| Benchmark | GPT-6 Luna | Muse Spark 1.2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 15 | ||||
| LMArena Elo | 1442.9 ↗ | 1493.5 ↗ | -50.6 | Muse Spark 1.2 |
| APEX-Agents (Mercor) | 44.3% ↗ | 36.4% ↗ | +7.9 pt | GPT-6 Luna |
| DeepSWE v1.1 | 66.6% ↗ | 59.3% ↗ | +7.3 pt | GPT-6 Luna |
| LiveBench Agentic Coding (LiveBench) | 51.2% ↗ | 57.6% ↗ | -6.4 pt | Muse Spark 1.2 |
| LiveBench Coding (LiveBench) | 79% ↗ | 77.5% ↗ | +1.5 pt | GPT-6 Luna |
| LiveBench Data Analysis (LiveBench) | 73.4% ↗ | 76.5% ↗ | -3.1 pt | Muse Spark 1.2 |
| LiveBench Instruction Following (LiveBench) | 55.9% ↗ | 74.3% ↗ | -18.4 pt | Muse Spark 1.2 |
| LiveBench Language (LiveBench) | 73.8% ↗ | 78.6% ↗ | -4.8 pt | Muse Spark 1.2 |
| LiveBench Mathematics (LiveBench) | 89.1% ↗ | 91.2% ↗ | -2.1 pt | Muse Spark 1.2 |
| LiveBench Reasoning (LiveBench) | 81.8% ↗ | 90% ↗ | -8.2 pt | Muse Spark 1.2 |
| LMArena Agent (LMArena) | 0.0135 ↗ | -0.0327 ↗ | 0 | Tie |
| LMArena WebDev (LMArena) | 1578.7 ↗ | 1531.8 ↗ | +46.9 | GPT-6 Luna |
| SAGE (Vals AI) | 48.1% ↗ | 47.7% ↗ | +0.4 pt | GPT-6 Luna |
| SimpleQA Verified | 41.4% ↗epoch run | 60.3% ↗epoch run | -18.9 pt | Muse Spark 1.2 |
| Terminal-Bench 4.0 (Vals AI) | 13.6% ↗ | 6.1% ↗ | +7.5 pt | GPT-6 Luna |
| Only GPT-6 Luna reports · 7 | ||||
| GPQA Diamond | 90.5% ↗epoch run | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 31% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 56.1% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 78.9% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 44.2% ↗epoch run | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 7% ↗epoch run | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.9% ↗epoch run | not reported | — | — |
| Only Muse Spark 1.2 reports · 8 | ||||
| DeepSWE v1.1 (Datacurve) | not reported | 54.9% ↗ | — | — |
| FrontierSWE V2 (Proximal Labs) | not reported | 12% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1292.8 ↗ | — | — |
| MCP Atlas | not reported | 90.3% ↗ | — | — |
| SimpleBench (SimpleBench) | not reported | 74.5% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 82.9% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 75.9% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 60.3% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GPT-6 Luna minus Muse Spark 1.2 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | GPT-6 Luna | Muse Spark 1.2 | Edge |
|---|---|---|---|
| Context window | 1.1M tokens | 1.0M tokens | GPT-6 Luna |
| Max output | 128K tokens | — | — |
| Input price / 1M | $0.1 ↗ | $1.25 ↗ | GPT-6 Luna |
| Output price / 1M | $0.5 ↗ | $4.25 ↗ | GPT-6 Luna |
| Cached input / 1M | $0.01 ↗ | $0.15 ↗ | GPT-6 Luna |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $0.6 | $5.5 | GPT-6 Luna |
| Modalities | text · vision | text · vision · video · audio | Muse Spark 1.2 |
| Released | 2026-09-22 | 2026-08-05 | — |
| Cited benchmark scores | 22 | 23 | — |
Reliability
Provider status
Live from /statusMore matchups
GPT-6 Luna vs …
Models sharing the most benchmarksMore matchups
Muse Spark 1.2 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-6 Luna and Muse Spark 1.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.