Model comparison
Gemini 3 Flash Preview vs Muse Spark 1.2
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 49.8 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
MetaSummary
- They share 22 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 5 categories and Muse Spark 1.2 in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 3 Flash Preview leads 38.6 to 29.5.
- The biggest single-benchmark swing is ProofBench: 15% for Gemini 3 Flash Preview and 43% for Muse Spark 1.2.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
Side by side
| Gemini 3 Flash Preview | Muse Spark 1.2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 52.3 | 49.8 |
| Released | 2025-12-17 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.50 | $1.25 |
| Output $ / M tokens | $3 | $4.25 |
| Results tracked | 59 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.5 (#35), Muse Spark 1.2: 48.6 (#49)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1439 | 1532 |
| WeirdML | 61.6% | 60.3% |
| LMArena Coding | 1460 | 1497 |
| SWE-bench Verified | 75.4% | — |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| GSO | 9.8% | — |
| ALE-Bench | 1,367 | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.6 (#27), Muse Spark 1.2: 29.5 (#77)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| GDP.pdf | 10% | 16% |
| Terminal-Bench | 64.3% | — |
| APEX-Agents | — | 36.4% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Muse Spark 1.2 leads
Gemini 3 Flash Preview: 49.2 (#35), Muse Spark 1.2: 50.4 (#32)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 61.1% | 74.5% |
| NYT Connections (extended) | 83.1% | 79.2% |
| LMArena Hard Prompts | 1465 | 1490 |
| DTBench | 89.1% | 94.7% |
| LMCA | 43.1% | 48.4% |
| Epoch Capabilities Index | 151.83 | 155.18 |
| ARC-AGI-2 | 33.6% | — |
| ARC-AGI-1 | 84.7% | — |
| CritPt | — | 17.7% |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 26% | — |
| ForecastBench | 58.5 | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.4 (#42), Muse Spark 1.2: 43.8 (#68)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 15% | 43% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| LMArena Math | 1472 | — |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#30), Muse Spark 1.2: 53.9 (#49)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 66.8% | 60.3% |
| LMArena Expert | 1461 | 1485 |
| GPQA Diamond | 89.4% | — |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.3 (#15), Muse Spark 1.2: 42.6 (#24)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1285 | 1304 |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Muse Spark 1.2 leads
Gemini 3 Flash Preview: 55.9 (#26), Muse Spark 1.2: 57.4 (#10)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1458 | 1479 |
| LMArena Chinese | 1510 | 1519 |
| LMArena Russian | 1480 | 1494 |
| LMArena French | 1478 | — |
| LMArena German | 1497 | — |
| LMArena Japanese | 1488 | — |
| LMArena Korean | 1443 | — |
| LMArena Spanish | 1470 | — |
Instruction Following Muse Spark 1.2 leads
Gemini 3 Flash Preview: 75.8 (#52), Muse Spark 1.2: 77.1 (#30)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1466 |
Long Context Muse Spark 1.2 leads
Gemini 3 Flash Preview: 44.4 (#63), Muse Spark 1.2: 45.4 (#35)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1452 | 1483 |
Writing & Preference Muse Spark 1.2 leads
Gemini 3 Flash Preview: 65.6 (#44), Muse Spark 1.2: 72.6 (#14)
| Benchmark | Gemini 3 Flash Preview | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1466 | 1486 |
| LMArena Creative Writing | 1457 | 1444 |
| LMArena Multi-Turn | 1471 | 1504 |
| EQ-Bench Creative Writing | — | 1840 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Muse Spark 1.2?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 49.8 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Muse Spark 1.2?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Gemini 3 Flash Preview or Muse Spark 1.2 better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3 Flash Preview and Muse Spark 1.2 share?
22 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Muse Spark 1.2 has 28.