Compare / head-to-head
Gemini 3.1 Pro Previewvs
Muse Spark 1.2
Muse Spark 1.2 leads 11 of 19 shared benchmarks. Muse Spark 1.2 is 2.5x cheaper per token. Both offer a 1.0M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
7 – 11
Muse Spark 1.2 leads · 1 tied
Cheaper per token
Muse Spark 1.2
2.5x cheaper, input + output
Larger context
Tie
both 1.0M tokens
Providers
2 providers
Google · Meta
Gemini 3.1 Pro Preview
Google · released 2026-02-19
textvisionaudio
Muse Spark 1.2
Meta · released 2026-08-05
textvisionvideoaudio
Quality
Benchmark matrix
19 shared · 17 only Gemini 3.1 Pro Preview · 4 only Muse Spark 1.2| Benchmark | Gemini 3.1 Pro Preview | Muse Spark 1.2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 19 | ||||
| LMArena Elo | 1480.1 ↗ | 1493.5 ↗ | -13.4 | Muse Spark 1.2 |
| APEX-Agents (Mercor) | 35.3% ↗ | 36.4% ↗ | -1.1 pt | Muse Spark 1.2 |
| DeepSWE v1.1 (Datacurve) | 11.7% ↗ | 54.9% ↗ | -43.2 pt | Muse Spark 1.2 |
| LiveBench Agentic Coding (LiveBench) | 44.1% ↗ | 57.6% ↗ | -13.5 pt | Muse Spark 1.2 |
| LiveBench Coding (LiveBench) | 76.5% ↗ | 77.5% ↗ | -1 pt | Muse Spark 1.2 |
| LiveBench Data Analysis (LiveBench) | 78.5% ↗ | 76.5% ↗ | +2 pt | Gemini 3.1 Pro Preview |
| LiveBench Instruction Following (LiveBench) | 79.1% ↗ | 74.3% ↗ | +4.8 pt | Gemini 3.1 Pro Preview |
| LiveBench Language (LiveBench) | 85.4% ↗ | 78.6% ↗ | +6.8 pt | Gemini 3.1 Pro Preview |
| LiveBench Mathematics (LiveBench) | 91% ↗ | 91.2% ↗ | -0.2 pt | Muse Spark 1.2 |
| LiveBench Reasoning (LiveBench) | 84% ↗ | 90% ↗ | -6 pt | Muse Spark 1.2 |
| LMArena Agent (LMArena) | -0.0771 ↗ | -0.0327 ↗ | 0 | Tie |
| LMArena Vision (LMArena) | 1279.3 ↗ | 1292.8 ↗ | -13.5 | Muse Spark 1.2 |
| LMArena WebDev (LMArena) | 1446.2 ↗ | 1531.8 ↗ | -85.6 | Muse Spark 1.2 |
| SAGE (Vals AI) | 48.7% ↗ | 47.7% ↗ | +1 pt | Gemini 3.1 Pro Preview |
| SimpleBench (SimpleBench) | 79.6% ↗ | 74.5% ↗ | +5.1 pt | Gemini 3.1 Pro Preview |
| SimpleQA Verified | 73.5% ↗epoch run | 60.3% ↗epoch run | +13.2 pt | Gemini 3.1 Pro Preview |
| Terminal-Bench 4.0 (Vals AI) | 2.5% ↗ | 6.1% ↗ | -3.6 pt | Muse Spark 1.2 |
| Toolathlon-Verified (HKUST) | 61.1% ↗ | 75.9% ↗ | -14.8 pt | Muse Spark 1.2 |
| WeirdML (Håvard Tveit Ihle) | 72.1% ↗ | 60.3% ↗ | +11.8 pt | Gemini 3.1 Pro Preview |
| Only Gemini 3.1 Pro Preview reports · 17 | ||||
| GPQA Diamond | 94.3% ↗ | not reported | — | — |
| AIME 2026 | 98.3% ↗matharena ⚠ | not reported | — | — |
| ARC-AGI-2 | 77.1% ↗ | not reported | — | — |
| BALROG (BALROG) | 57% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 55% ↗epoch run | not reported | — | — |
| EBR-bench (Epoch AI run) | 14.3% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 26.8% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 59.6% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 26.7% ↗epoch run | not reported | — | — |
| GSO Opt@1 (GSO) | 21.6% ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 8.9% ↗epoch run | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 34% ↗epoch run | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 95.6% ↗epoch run | not reported | — | — |
| SWE-Bench Pro | 54.2% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 75.6% ↗epoch run | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 26% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 3774.25 ↗ | not reported | — | — |
| Only Muse Spark 1.2 reports · 4 | ||||
| DeepSWE v1.1 | not reported | 59.3% ↗ | — | — |
| FrontierSWE V2 (Proximal Labs) | not reported | 12% ↗ | — | — |
| MCP Atlas | not reported | 90.3% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 82.9% ↗ | — | — |
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 3.1 Pro Preview 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 | Gemini 3.1 Pro Preview | Muse Spark 1.2 | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 1.0M tokens | Tie |
| Max output | 66K tokens | — | — |
| Input price / 1M | $2 ↗ | $1.25 ↗ | Muse Spark 1.2 |
| Output price / 1M | $12 ↗ | $4.25 ↗ | Muse Spark 1.2 |
| Cached input / 1M | $0.2 ↗ | $0.15 ↗ | Muse Spark 1.2 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $14 | $5.5 | Muse Spark 1.2 |
| Modalities | text · vision · audio | text · vision · video · audio | Muse Spark 1.2 |
| Released | 2026-02-19 | 2026-08-05 | — |
| Cited benchmark scores | 43 | 23 | — |
Reliability
Provider status
Live from /statusMore matchups
Gemini 3.1 Pro Preview 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 Gemini 3.1 Pro Preview and Muse Spark 1.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.