Muse Spark 1.3 vs Qwen3.8 Max Preview
Wins 4 of 8 areas
Reasoning · Math · Long documents · Following instructions
Wins 1 of 8 areas
Agents
Muse Spark 1.3 wins more areas, narrowly.Qwen3.8 Max Preview is better at agents.
Scores updated · 30 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.
- ReasoningHard problems that need careful thinking30Muse Spark 1.33 of 4 tests · 1 tie
- MathCompetition and research-level math10Muse Spark 1.31 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Muse Spark 1.31 of 1 test
- Following instructionsDoing exactly what it is asked10Muse Spark 1.31 of 1 test
- AgentsCarrying out multi-step tasks on its own12Qwen3.8 Max Preview2 of 4 tests · 1 tie
- CodingWriting and fixing software22Even2 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 2 ties
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.
Muse Spark 1.3 costs 31% 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
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.9points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+8.2points ahead
- Research-level physics problemsCritPt+7.2points ahead
Where Qwen3.8 Max Preview pulls ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+7.1points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+5.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+4.5points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- LiveBench · CodingMuse Spark 1.3 by 8.281.172.9+8.2
- SciCodeMuse Spark 1.3 by 6.758.852.1+6.7
- Terminal-Bench 2.1Qwen3.8 Max Preview by 4.584.388.8+4.5
- LMArena · WebDevQwen3.8 Max Preview by 13 rating points16591672+13 rating
- LiveBench · Agentic Codingtie64.164.7tie
AgentsQwen3.8 Max Preview
- AA IT-Bench SREQwen3.8 Max Preview by 7.133.240.3+7.1
- Terminal-Bench 4.0Qwen3.8 Max Preview by 5.633.338.9+5.6
- τ-Bench V3 · BankingMuse Spark 1.3 by 2.750.547.8+2.7
- GDPValtie5958.3tie
ReasoningMuse Spark 1.3
- CritPtMuse Spark 1.3 by 7.224.917.7+7.2
- Humanity's Last ExamMuse Spark 1.3 by 5.648.743.1+5.6
- LiveBench · ReasoningMuse Spark 1.3 by 1.589.788.2+1.5
- GPQA Diamondtie93.592.8tie
FactsEven
- AA-Omniscience · AccuracyMuse Spark 1.3 by 11.943.631.7+11.9
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 4.167.171.2+4.1
Images and chartsEven
- MMMU-Protie8282.8tie
- LMArena · Visiontie13081313tie
MathMuse Spark 1.3
- LiveBench · MathematicsMuse Spark 1.3 by 4.79691.3+4.7
- FrontierMath Tiers 1-3 (v2)tie7474.7tie
- FrontierMath Tier 4tie46.346.3tie
Following instructionsMuse Spark 1.3
- LiveBench · Instruction FollowingMuse Spark 1.3 by 3.97874.1+3.9
Other results8 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.
- DeepSWE 1.1Muse Spark 1.3 by 18.875.456.6+18.8
- AA-OmniscienceMuse Spark 1.3 by 132512+13
- JobBenchMuse Spark 1.3 by 11.564.953.4+11.5
- AA Agentic IndexMuse Spark 1.3 by 6.155.749.6+6.1
- Artificial Analysis Coding IndexMuse Spark 1.3 by 475.871.8+4
- livebench_languageMuse Spark 1.3 by 3.182.879.7+3.1
- AA IntelligenceMuse Spark 1.3 by 2.748.145.4+2.7
- livebench_data_analysisMuse Spark 1.3 by 1.279.678.4+1.2
Questions people ask
Which is better, Muse Spark 1.3 or Qwen3.8 Max Preview?
Muse Spark 1.3 wins four of the eight areas we test: reasoning, math, long documents and following instructions. Qwen3.8 Max Preview wins agents. They are level on coding, facts and images and charts.
Which is better for coding?
Neither. They win 2 coding tests each of the 5 both models report, and 1 is a tie.
Which is cheaper?
Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Muse Spark 1.3 about 31% cheaper for the same work.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.