Gemini 3.8 Flash vs Muse Spark 1.3
Wins 2 of 8 areas
Images and charts · Following instructions
Wins 4 of 8 areas
Coding · Agents · Math · Long documents
Muse Spark 1.3 wins more areas, narrowly.Gemini 3.8 Flash is cheaper and better at images and charts.
Scores updated · 32 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software14Muse Spark 1.34 of 5 tests
- MathCompetition and research-level math03Muse Spark 1.33 of 3 tests
- AgentsCarrying out multi-step tasks on its own13Muse Spark 1.33 of 4 tests
- Long documentsFinding answers in very long texts01Muse Spark 1.31 of 1 test
- Images and chartsUnderstanding pictures, charts and video10Gemini 3.8 Flash1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Gemini 3.8 Flash1 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 3 ties
- FactsGetting facts right instead of making them up11Even1 each
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Gemini 3.8 Flash costs 18% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Muse Spark 1.3 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+24.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.3points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+13.6points ahead
Where Gemini 3.8 Flash pulls ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+19.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11points ahead
- Harder college exam questions with imagesMMMU-Pro+3.6points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMuse Spark 1.3
- LiveBench · Agentic CodingMuse Spark 1.3 by 9.954.264.1+9.9
- LiveBench · CodingMuse Spark 1.3 by 8.672.581.1+8.6
- LMArena · WebDevMuse Spark 1.3 by 74 rating points15851659+74 rating
- Terminal-Bench 2.1Gemini 3.8 Flash by 3.387.684.3+3.3
- SciCodeMuse Spark 1.3 by 2.256.658.8+2.2
AgentsMuse Spark 1.3
- AA IT-Bench SREGemini 3.8 Flash by 19.352.533.2+19.3
- Terminal-Bench 4.0Muse Spark 1.3 by 13.619.733.3+13.6
- GDPValMuse Spark 1.3 by 12.246.859+12.2
- τ-Bench V3 · BankingMuse Spark 1.3 by 5.644.950.5+5.6
ReasoningEven
- CritPtMuse Spark 1.3 by 6.618.324.9+6.6
- GPQA DiamondGemini 3.8 Flash by 1.895.393.5+1.8
- Humanity's Last Examtie47.848.7tie
- SimpleBenchtie82.481.8tie
- LiveBench · Reasoningtie89.389.7tie
FactsEven
- AA-Omniscience · Non-hallucinationMuse Spark 1.3 by 22.344.867.1+22.3
- AA-Omniscience · AccuracyGemini 3.8 Flash by 1154.643.6+11
Images and chartsGemini 3.8 Flash
- MMMU-ProGemini 3.8 Flash by 3.685.682+3.6
- LMArena · Visiontie13151308tie
MathMuse Spark 1.3
- FrontierMath Tier 4Muse Spark 1.3 by 24.321.946.3+24.3
- FrontierMath Tiers 1-3 (v2)Muse Spark 1.3 by 5.668.474+5.6
- LiveBench · MathematicsMuse Spark 1.3 by 4.491.696+4.4
Following instructionsGemini 3.8 Flash
- LiveBench · Instruction FollowingGemini 3.8 Flash by 3.481.478+3.4
Other results9 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- livebench_data_analysisMuse Spark 1.3 by 25.65479.6+25.6
- HiL-Bench (Tools-allowed)Muse Spark 1.3 by 25.441.566.9+25.4
- AA Agentic IndexMuse Spark 1.3 by 14.641.155.7+14.6
- OSWorld 2.0Muse Spark 1.3 by 7.95966.9+7.9
- AA IntelligenceMuse Spark 1.3 by 7.240.948.1+7.2
- livebench_languageGemini 3.8 Flash by 587.882.8+5
- AA-OmniscienceGemini 3.8 Flash by 4.629.625+4.6
- DeepSWE 1.1Muse Spark 1.3 by 1.773.775.4+1.7
- Artificial Analysis Coding Indextie76.375.8tie
Questions people ask
Which is better, Gemini 3.8 Flash or Muse Spark 1.3?
Muse Spark 1.3 wins four of the eight areas we test: coding, agents, math and long documents. Gemini 3.8 Flash wins images and charts and following instructions, and costs 18% less. They are level on reasoning and facts.
Which is better for coding?
Muse Spark 1.3. It wins 4 of the 5 coding tests both models report; Gemini 3.8 Flash wins 1.
Which is cheaper?
Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Muse Spark 1.3 costs $1.25 and $4.25. That makes Gemini 3.8 Flash about 18% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.