Model comparison
Gemini 3.8 Flash vs Muse Spark 1.3
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.8 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 7 categories and Muse Spark 1.3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.8 Flash leads 74.8 to 42.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 22% for Gemini 3.8 Flash and 46.3% for Muse Spark 1.3.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
Side by side
| Gemini 3.8 Flash | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 61.8 | 54.8 |
| Released | 2026-09-02 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.75 | $1.25 |
| Output $ / M tokens | $3.75 | $4.25 |
| Results tracked | 50 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 59.2 (#15), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| CursorBench | 39.6% | 41.6% |
| LMArena WebDev | 1584 | 1657 |
| SciCode | 56.6% | 59.7% |
| LMArena Coding | 1510 | 1514 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| FrontierSWE | 19.6% | — |
| WeirdML | 84.8% | — |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.8 Flash: 41.8 (#21), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 64.3% | 57.8% |
| GDP.pdf | 23.4% | 27.6% |
| Remote Labor Index | 5.8% | — |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 97.4% | 85.1% |
| CritPt | 18.3% | 26% |
| Chess Puzzles | 61% | 38% |
| LMArena Hard Prompts | 1508 | 1503 |
| Mystery Game Puzzles | 47% | 25% |
| DTBench | 95.7% | 96.5% |
| LMCA | 52.9% | 53.9% |
| Epoch Capabilities Index | 156.71 | 156.75 |
| ARC-AGI-2 | 89.2% | — |
| ARC-AGI-1 | 98.5% | — |
| Surface Evolver Bench | 76.9% | — |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
Gemini 3.8 Flash: 65.3 (#28), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 74.4% |
| FrontierMath Tier 4 | 22% | 46.3% |
| OTIS Mock AIME 2024-2025 | 98.9% | 99.2% |
| ProofBench | 48% | 58% |
| LMArena Math | 1528 | 1494 |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1524 | 1516 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
Multimodal Muse Spark 1.3 leads
Gemini 3.8 Flash: 40.7 (#45), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1314 | 1309 |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
| LMArena Document | — | 1471 |
Multilingual Too close to call
Gemini 3.8 Flash: 58.0 (#5), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1491 | 1481 |
| LMArena Chinese | 1554 | 1529 |
| LMArena French | 1498 | 1524 |
| LMArena German | 1493 | 1515 |
| LMArena Japanese | 1502 | 1474 |
| LMArena Korean | 1459 | 1501 |
| LMArena Russian | 1515 | 1490 |
| LMArena Spanish | 1485 | 1490 |
Instruction Following Too close to call
Gemini 3.8 Flash: 78.0 (#13), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1490 | 1477 |
Long Context Too close to call
Gemini 3.8 Flash: 46.3 (#24), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1508 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Gemini 3.8 Flash: 72.2 (#15), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1499 | 1490 |
| LMArena Creative Writing | 1492 | 1455 |
| EQ-Bench Creative Writing | 1748 | 1906 |
| LMArena Multi-Turn | 1501 | 1482 |
Frequently asked questions
Is Gemini 3.8 Flash better than Muse Spark 1.3?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.8 on the Noometry Index.
Which is cheaper, Gemini 3.8 Flash or Muse Spark 1.3?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Gemini 3.8 Flash or Muse Spark 1.3 better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 56.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.8 Flash and Muse Spark 1.3 share?
35 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Muse Spark 1.3 has 37.