Model comparison
Gemini 2.5 Flash-Lite vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 11× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Google
MetaSummary
- They share 19 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 0 categories and Muse Spark 1.3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 72.4 to 35.5.
- The biggest single-benchmark swing is LMCA: 18.1% for Gemini 2.5 Flash-Lite and 53.9% for Muse Spark 1.3.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
Side by side
| Gemini 2.5 Flash-Lite | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 36.4 | 54.4 |
| Released | 2025-06-17 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $1.25 |
| Output $ / M tokens | $0.40 | $4.25 |
| Results tracked | 33 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 38.0 (#167), Muse Spark 1.3: 56.1 (#18)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Coding | 1373 | 1516 |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1655 |
| SciCode | — | 59.7% |
| WeirdML | 35.2% | — |
| ALE-Bench | 325.9 | — |
Agentic & Tool Use Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 27.8 (#89), Muse Spark 1.3: 38.6 (#28)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 36.9% | — |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Muse Spark 1.3: 52.9 (#27)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1503 |
| DTBench | 62.8% | 96.5% |
| LMCA | 18.1% | 53.9% |
| Epoch Capabilities Index | 133.93 | 156.89 |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 24.9% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Muse Spark 1.3: 72.4 (#16)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Math | 1373 | 1497 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| Omni-MATH | 48% | — |
Knowledge Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Muse Spark 1.3: 42.0 (#92)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1373 | 1516 |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 28.6 (#109), Muse Spark 1.3: 43.0 (#21)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1198 | 1310 |
| VPCT | 30% | — |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 49.5 (#129), Muse Spark 1.3: 57.8 (#6)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1369 | 1485 |
| LMArena Chinese | 1404 | 1527 |
| LMArena French | 1388 | 1534 |
| LMArena Korean | 1358 | 1513 |
| LMArena Russian | 1373 | 1491 |
| LMArena Spanish | 1396 | 1485 |
| LMArena German | 1390 | — |
| LMArena Japanese | 1359 | — |
Instruction Following Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 70.2 (#163), Muse Spark 1.3: 77.8 (#14)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1366 | 1481 |
| IFEval | 81% | — |
Long Context Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Muse Spark 1.3: 45.7 (#29)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1373 | 1491 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Muse Spark 1.3 leads
Gemini 2.5 Flash-Lite: 57.0 (#130), Muse Spark 1.3: 73.7 (#10)
| Benchmark | Gemini 2.5 Flash-Lite | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1379 | 1490 |
| LMArena Creative Writing | 1366 | 1450 |
| LMArena Multi-Turn | 1367 | 1486 |
| EQ-Bench Creative Writing | — | 1906 |
| WildBench | 81.8% | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 11× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or Muse Spark 1.3?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Gemini 2.5 Flash-Lite or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 2.5 Flash-Lite and Muse Spark 1.3 share?
19 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Muse Spark 1.3 has 34.