Comparing 2 models

Gemini 3.1 Pro Preview vs Muse Spark 1.3

Benchmarks through

Verdict

Gemini 3.1 Pro Preview places higher on 9 of the 9 tasks where both are ranked. Muse Spark 1.3 costs 1.6x less per input token.

  • Choose Gemini 3.1 Pro Preview for Chat & Roleplay (#3), Roleplay & Character (#3), Creative Writing (#3).

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.

metric
Model 1Gemini 3.1 Pro Preview
Model 2Muse Spark 1.3
Best for
Business Writing (#3)
Charts & Diagrams (#3)
Provider
google
meta
Context
1.0MBest
1.0MBest
Input / 1M
$2
$1.25Best
Output / 1M
$12
$4.25Best
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
—
—
Released
Feb 19, 2026
Sep 2, 2026

Measured head to head

Benchmarks both models were run on

EvaluationGemini 3.1 Pro PreviewMuse Spark 1.3Source
Design Arena Coding1220 Elo1351 Elosource · 2026-11-15
Design Arena Full-stack Agent1041 Elo1269 Elosource · 2026-11-15
Design Arena UI1215 Elo1346 Elosource · 2026-11-15
Design Arena Web-app Agent1103 Elo1273 Elosource · 2026-11-15
Design Arena Website1225 Elo1352 Elosource · 2026-11-15
FrontierMath Tiers 1-3 (Epoch AI)59.6% ± 2.974.4% ± 2.6source · 2026-06-11
LiveBench Agentic Coding44.1%64.1%source · 2026-10-18
LiveBench Coding76.5%81.1%source · 2026-10-18
LiveBench Data Analysis78.5%79.6%source · 2026-10-18
LiveBench Instruction Following79.1%78%source · 2026-10-18
LiveBench Language85.4%82.8%source · 2026-10-18
LiveBench Math91.0%96.0%source · 2026-10-18
LiveBench Reasoning84%89.7%source · 2026-10-18
LMArena Agent-4.52.2source · 2026-11-11
LMArena Agent Bash Recovery-23.36.1source · 2026-10-08
LMArena Agent Steerability-8.22.6source · 2026-11-11
LMArena Agent Task Outcome-11.33.7source · 2026-11-11
LMArena Agent Tool Hallucination-0.40.8source · 2026-11-11
LMArena Creative Writing1483 Elo1467 Elosource · 2026-11-11
LMArena Instruction Following1465 Elo1479 Elosource · 2026-11-11
LMArena Long Query1482 Elo1489 Elosource · 2026-11-11
LMArena Math1485 Elo1498 Elosource · 2026-11-11
LMArena Text1487 Elo1497 Elosource · 2026-11-11
LMArena Text Factuality1472 Elo1481 Elosource · 2026-11-11
LMArena Vision1280 Elo1291 Elosource · 2026-11-09
LMArena Vision Diagrams1309 Elo1329 Elosource · 2026-11-09
LMArena Vision OCR1295 Elo1309 Elosource · 2026-11-09
LMArena WebDev1446 Elo1655 Elosource · 2026-11-11
LMArena WebDev Image-to-Web1480 Elo1637 Elosource · 2026-11-10
OTIS Mock AIME (Epoch AI)95.6% ± 3.199.2% ± 0.6source · 2026-08-06
OTIS Mock AIME (Epoch AI)95.6% ± 3.199.2% ± 0.6source · 2026-02-20

Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.