Compare / head-to-head
Gemini 3 Flash Previewvs
Muse Spark
Muse Spark leads 4 of 7 shared benchmarks.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 4
Muse Spark leads
Cheaper per token
—
list price, input + output
Larger context
—
both 1.0M tokens
Providers
2 providers
Google · Meta
Gemini 3 Flash Preview
Google · released 2025-12-17
textvisionaudio
- Context
- 1.0M
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 34 · 12 core
Muse Spark
Meta · released 2026-04-08
textvision
- Context
- —
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 19 · 8 core
Quality
Benchmark matrix
7 shared · 19 only Gemini 3 Flash Preview · 11 only Muse Spark| Benchmark | Gemini 3 Flash Preview | Muse Spark | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| SWE-bench Verified | 78% ↗ | 77.4% ↗ | +0.6 pt | Gemini 3 Flash Preview |
| GPQA Diamond | 90.4% ↗ | 89.5% ↗ | +0.9 pt | Gemini 3 Flash Preview |
| Humanity's Last Exam (no tools) | 33.7% ↗ | 42.8% ↗ | -9.1 pt | Muse Spark |
| LMArena Elo | 1472.7 ↗ | 1489.3 ↗ | -16.6 | Muse Spark |
| LMArena Vision (LMArena) | 1272.9 ↗ | 1293.6 ↗ | -20.7 | Muse Spark |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 95.6% ↗epoch run | 88.9% ↗epoch run | +6.7 pt | Gemini 3 Flash Preview |
| Terminal-Bench 2.0 | 47.6% ↗ | 59% ↗ | -11.4 pt | Muse Spark |
| Only Gemini 3 Flash Preview reports · 19 | ||||
| AIME 2025 | 95.2% ↗ | not reported | — | — |
| BALROG (BALROG) | 48.1% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 40% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 17.1% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 51.2% ↗epoch run | not reported | — | — |
| GSO Opt@1 (GSO) | 7.8% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1438.9 ↗ | not reported | — | — |
| MMMU-Pro | 81.2% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 26% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 51.8% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 61.1% ↗ | not reported | — | — |
| SimpleQA Verified | 68.7% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 75.4% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 82.5% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 27.3% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 76.8% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 91.2% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 3634.72 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 61.6% ↗ | not reported | — | — |
| Only Muse Spark reports · 11 | ||||
| ARC AGI 2 (Public) | not reported | 42.5% ↗ | — | — |
| CharXiv Reasoning | not reported | 86.4% ↗ | — | — |
| DeepSearchQA | not reported | 74.8% ↗ | — | — |
| HealthBench Hard | not reported | 42.8% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 50.4% ↗ | — | — |
| LiveCodeBench Pro | not reported | 80% ↗ | — | — |
| MedXpertQA (MM) | not reported | 78.4% ↗ | — | — |
| MMMU Pro | not reported | 80.4% ↗ | — | — |
| ScreenSpot Pro (With Python) | not reported | 84.1% ↗ | — | — |
| SimpleVQA | not reported | 71.3% ↗ | — | — |
| SWE-Bench Pro | not reported | 52.4% ↗ | — | — |
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 Flash Preview minus Muse Spark 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 Flash Preview | Muse Spark | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | — | — |
| Max output | 66K tokens | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text · vision · audio | text · vision | Gemini 3 Flash Preview |
| Released | 2025-12-17 | 2026-04-08 | — |
| Cited benchmark scores | 34 | 19 | — |
Reliability
Provider status
Live from /statusMore matchups
Gemini 3 Flash Preview vs …
Models sharing the most benchmarksMore matchups
Muse Spark vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 3 Flash Preview and Muse Spark on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.