Model comparison
Gemini 3.5 Flash vs Muse Spark 1.2
Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 1.7× less per token, which makes it the better buy when Gemini 3.5 Flash's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Google
MetaSummary
- They share 29 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 7 categories and Muse Spark 1.2 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.5 Flash leads 60.7 to 46.4.
- The biggest single-benchmark swing is DeepSWE: 37.4% for Gemini 3.5 Flash and 54.9% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.50 / $9 for Gemini 3.5 Flash.
Side by side
| Gemini 3.5 Flash | Muse Spark 1.2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 54.2 | 50.3 |
| Released | 2026-05-19 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $1.50 | $1.25 |
| Output $ / M tokens | $9 | $4.25 |
| Results tracked | 54 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.5 Flash: 49.4 (#49), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| DeepSWE | 37.4% | 54.9% |
| LMArena WebDev | 1499 | 1533 |
| SciCode | 53.1% | 56.4% |
| WeirdML | 62.6% | 60.3% |
| LMArena Coding | 1492 | 1495 |
| SWE-bench Verified | 79.3% | — |
| FrontierSWE | — | 12% |
| ALE-Bench | 911.02 | — |
Agentic & Tool Use Muse Spark 1.2 leads
Gemini 3.5 Flash: 24.7 (#114), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | 27.5% | 36.4% |
| GDP.pdf | 14% | 16% |
| GBAEval | 6.7% | — |
| Vending-Bench 2 | 5,396 | — |
Reasoning Gemini 3.5 Flash leads
Gemini 3.5 Flash: 62.8 (#18), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 76.7% | 74.5% |
| NYT Connections (extended) | 92.6% | 79.2% |
| CritPt | 13.1% | 17.7% |
| LMArena Hard Prompts | 1488 | 1486 |
| DTBench | 94.7% | 94.7% |
| LMCA | 47.1% | 48.4% |
| Epoch Capabilities Index | 154.46 | 154.87 |
| ARC-AGI-2 | 72.1% | — |
| ARC-AGI-1 | 92.5% | — |
| Chess Puzzles | 50% | — |
| EnigmaEval | 25.4% | — |
| EBR-Bench | 4.8% | — |
| Mystery Game Puzzles | 32% | — |
| Surface Evolver Bench | 58.1% | — |
| ForecastBench | 59 | — |
Math Gemini 3.5 Flash leads
Gemini 3.5 Flash: 60.7 (#36), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 31% | 43% |
| LMArena Math | 1504 | 1471 |
| FrontierMath (Tiers 1-3) | 62.8% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Gemini 3.5 Flash leads
Gemini 3.5 Flash: 66.3 (#11), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 66.2% | 60.3% |
| LMArena Expert | 1495 | 1480 |
| GPQA Diamond | 92.8% | — |
Multimodal Gemini 3.5 Flash leads
Gemini 3.5 Flash: 45.7 (#15), Muse Spark 1.2: 43.4 (#25)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1310 | 1305 |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |
Multilingual Too close to call
Gemini 3.5 Flash: 57.0 (#13), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1476 | 1478 |
| LMArena Chinese | 1526 | 1511 |
| LMArena French | 1490 | 1513 |
| LMArena Russian | 1493 | 1487 |
| LMArena Spanish | 1480 | 1498 |
| LMArena German | 1492 | — |
| LMArena Japanese | 1486 | — |
| LMArena Korean | 1451 | — |
Instruction Following Too close to call
Gemini 3.5 Flash: 77.0 (#30), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1467 | 1461 |
Long Context Too close to call
Gemini 3.5 Flash: 45.4 (#38), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1482 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Gemini 3.5 Flash: 65.5 (#47), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Gemini 3.5 Flash | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1482 | 1482 |
| LMArena Creative Writing | 1470 | 1449 |
| LMArena Multi-Turn | 1481 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
| EQ-Bench 4 | 1087 | — |
Frequently asked questions
Is Gemini 3.5 Flash better than Muse Spark 1.2?
Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 1.7× less per token, which makes it the better buy when Gemini 3.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Gemini 3.5 Flash lists at $1.50 and $9.
Is Gemini 3.5 Flash or Muse Spark 1.2 better for coding?
They score almost the same on coding (49.4 vs 49.2); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.5 Flash and Muse Spark 1.2 share?
29 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Muse Spark 1.2 has 31.