Compare / head-to-head
Gemini 4 Argonvs
Muse Spark 1.1
Gemini 4 Argon leads 7 of 7 shared benchmarks. Muse Spark 1.1 is 2.2x cheaper per token.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
7 – 0
Gemini 4 Argon leads
Cheaper per token
Muse Spark 1.1
2.2x cheaper, input + output
Larger context
—
unknown
Providers
2 providers
Google · Meta
Gemini 4 Argon
Google · released 2026-09-30
textvisionvideo
Muse Spark 1.1
Meta · released 2026-07-09
textvisionvideoaudio
Quality
Benchmark matrix
7 shared · 5 only Gemini 4 Argon · 23 only Muse Spark 1.1| Benchmark | Gemini 4 Argon | Muse Spark 1.1 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| LMArena Elo | 1525.2 ↗ | 1491.3 ↗ | +33.9 | Gemini 4 Argon |
| APEX-Agents (Mercor) | 82.2% ↗ | 31.8% ↗ | +50.4 pt | Gemini 4 Argon |
| DeepSWE v1.1 | 77.9% ↗ | 53.3% ↗ | +24.6 pt | Gemini 4 Argon |
| LMArena Agent (LMArena) | 0.0757 ↗ | -0.0488 ↗ | +0.1 | Gemini 4 Argon |
| LMArena WebDev (LMArena) | 1679.5 ↗ | 1541.7 ↗ | +137.8 | Gemini 4 Argon |
| SAGE (Vals AI) | 53.6% ↗ | 45.6% ↗ | +8 pt | Gemini 4 Argon |
| Vending-Bench 2 (Andon Labs) | 13718.16 ↗ | 6520.48 ↗ | +7197.7 | Gemini 4 Argon |
| Only Gemini 4 Argon reports · 5 | ||||
| AutomationBench | 51.3% ↗ | not reported | — | — |
| CWE-bench v1 | 68% ↗ | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 55% ↗ | not reported | — | — |
| LVBench | 91.7% ↗ | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 57.6% ↗ | not reported | — | — |
| Only Muse Spark 1.1 reports · 23 | ||||
| BabyVision | not reported | 76.3% ↗ | — | — |
| CharXiv Reasoning | not reported | 88.4% ↗ | — | — |
| DeepSWE v1.1 (Datacurve) | not reported | 53.3% ↗ | — | — |
| Finance Agent v2 | not reported | 57.2% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 62.1% ↗ | — | — |
| JobBench | not reported | 54.7% ↗ | — | — |
| LiveBench Agentic Coding (LiveBench) | not reported | 58.5% ↗ | — | — |
| LiveBench Coding (LiveBench) | not reported | 77.2% ↗ | — | — |
| LiveBench Data Analysis (LiveBench) | not reported | 72.5% ↗ | — | — |
| LiveBench Instruction Following (LiveBench) | not reported | 69.6% ↗ | — | — |
| LiveBench Language (LiveBench) | not reported | 74.3% ↗ | — | — |
| LiveBench Mathematics (LiveBench) | not reported | 87.1% ↗ | — | — |
| LiveBench Reasoning (LiveBench) | not reported | 87.7% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1281.1 ↗ | — | — |
| MCP Atlas | not reported | 88.1% ↗ | — | — |
| OSWorld-Verified | not reported | 80.8% ↗ | — | — |
| OSWorld-Verified (XLANG) | not reported | 80.7% ↗ | — | — |
| SimpleQA Verified | not reported | 57.8% ↗epoch run | — | — |
| SWE-Bench Pro | not reported | 61.5% ↗ | — | — |
| tau2-bench Banking Knowledge (Sierra) | not reported | 40.5% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 80% ↗ | — | — |
| Toolathlon-Verified | not reported | 75.6% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 75.6% ↗ | — | — |
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 Gemini 4 Argon minus Muse Spark 1.1 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 | Gemini 4 Argon | Muse Spark 1.1 | Edge |
|---|---|---|---|
| Context window | — | 1.0M tokens | — |
| Max output | 1M tokens | — | — |
| Input price / 1M | $2 ↗ | $1.25 ↗ | Muse Spark 1.1 |
| Output price / 1M | $10 ↗ | $4.25 ↗ | Muse Spark 1.1 |
| Cached input / 1M | $0.1 ↗ | $0.15 ↗ | Gemini 4 Argon |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $12 | $5.5 | Muse Spark 1.1 |
| Modalities | text · vision · video | text · vision · video · audio | Muse Spark 1.1 |
| Released | 2026-09-30 | 2026-07-09 | — |
| Cited benchmark scores | 12 | 30 | — |
Reliability
Provider status
Live from /statusMore matchups
Gemini 4 Argon vs …
Models sharing the most benchmarksMore matchups
Muse Spark 1.1 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 4 Argon and Muse Spark 1.1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.