Comparing 2 models
Gemini 3.5 Flash vs Muse Spark 1.3
Benchmarks through
Verdict
Muse Spark 1.3 places higher on 11 of the 11 tasks where both are ranked. Muse Spark 1.3 costs 1.2x less per input token.
- Choose Muse Spark 1.3 for Chat & Roleplay (#4), Document Summarization (#4), Roleplay & Character (#4).
Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.
Measured head to head
Benchmarks both models were run on
| Evaluation | Gemini 3.5 Flash | Muse Spark 1.3 | Source |
|---|---|---|---|
| Design Arena Coding | 1256 Elo | 1351 Elo | source · 2026-11-15 |
| Design Arena Full-stack Agent | 1170 Elo | 1269 Elo | source · 2026-11-15 |
| Design Arena UI | 1265 Elo | 1346 Elo | source · 2026-11-15 |
| Design Arena Web-app Agent | 1177 Elo | 1273 Elo | source · 2026-11-15 |
| Design Arena Website | 1260 Elo | 1352 Elo | source · 2026-11-15 |
| FrontierMath Tiers 1-3 (Epoch AI) | 62.8% ± 2.9 | 74.4% ± 2.6 | source · 2026-06-10 |
| LiveBench Agentic Coding | 49.0% | 64.1% | source · 2026-10-18 |
| LiveBench Coding | 78.2% | 81.1% | source · 2026-10-18 |
| LiveBench Data Analysis | 64.9% | 79.6% | source · 2026-10-18 |
| LiveBench Instruction Following | 75.6% | 78% | source · 2026-10-18 |
| LiveBench Language | 84.6% | 82.8% | source · 2026-10-18 |
| LiveBench Math | 88.2% | 96.0% | source · 2026-10-18 |
| LiveBench Reasoning | 82% | 89.7% | source · 2026-10-18 |
| LMArena Creative Writing | 1469 Elo | 1467 Elo | source · 2026-11-11 |
| LMArena Instruction Following | 1467 Elo | 1479 Elo | source · 2026-11-11 |
| LMArena Long Query | 1484 Elo | 1489 Elo | source · 2026-11-11 |
| LMArena Math | 1504 Elo | 1498 Elo | source · 2026-11-11 |
| LMArena Text | 1478 Elo | 1497 Elo | source · 2026-11-11 |
| LMArena Text Factuality | 1478 Elo | 1481 Elo | source · 2026-11-11 |
| LMArena Vision | 1281 Elo | 1291 Elo | source · 2026-11-09 |
| LMArena Vision Diagrams | 1307 Elo | 1329 Elo | source · 2026-11-09 |
| LMArena Vision OCR | 1291 Elo | 1309 Elo | source · 2026-11-09 |
| LMArena WebDev | 1500 Elo | 1655 Elo | source · 2026-11-11 |
| LMArena WebDev Image-to-Web | 1500 Elo | 1637 Elo | source · 2026-11-10 |
| OTIS Mock AIME (Epoch AI) | 88.9% ± 4.7 | 99.2% ± 0.6 | source · 2026-08-06 |
| OTIS Mock AIME (Epoch AI) | 80% ± 6 | 99.2% ± 0.6 | source · 2026-07-15 |
| OTIS Mock AIME (Epoch AI) | 95.6% ± 2.7 | 99.2% ± 0.6 | source · 2026-05-25 |
Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.
task evidence
How they place when the question changes
Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.