Muse Spark 1.1 vs Qwen3.5 397B A17B
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Following instructions
Wins 0 of 7 areas
—
Muse Spark 1.1 is the stronger all-rounder.Qwen3.5 397B A17B is cheaper.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. 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 software40Muse Spark 1.14 of 4 tests
- AgentsCarrying out multi-step tasks on its own30Muse Spark 1.13 of 3 tests
- FactsGetting facts right instead of making them up30Muse Spark 1.13 of 3 tests
- ReasoningHard problems that need careful thinking20Muse Spark 1.12 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Muse Spark 1.11 of 1 test
- Following instructionsDoing exactly what it is asked10Muse Spark 1.11 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Images and charts, 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.
Qwen3.5 397B A17B costs 24% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Muse Spark 1.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+38.9points ahead
- Short factual questions, answered correctlySimpleQA Verified+31.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+26.6points ahead
Where Qwen3.5 397B A17B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMuse Spark 1.1
- Terminal-Bench 2.1Muse Spark 1.1 by 26.677.951.3+26.6
- LMArena · WebDevMuse Spark 1.1 by 142 rating points15421400+142 rating
- SciCodeMuse Spark 1.1 by 1458.844.8+14
- SWE-bench ProMuse Spark 1.1 by 10.661.550.9+10.6
AgentsMuse Spark 1.1
- GDPValMuse Spark 1.1 by 20.935.714.8+20.9
- τ-Bench V3 · BankingMuse Spark 1.1 by 18.431.813.4+18.4
- Terminal-Bench 4.0Muse Spark 1.1 by 6.16.10+6.1
ReasoningMuse Spark 1.1
- Humanity's Last ExamMuse Spark 1.1 by 17.246.229+17.2
- CritPtMuse Spark 1.1 by 13.415.11.7+13.4
- GPQA Diamondtie89.889.3tie
FactsMuse Spark 1.1
- AA-Omniscience · Non-hallucinationMuse Spark 1.1 by 38.95011.1+38.9
- SimpleQA VerifiedMuse Spark 1.1 by 31.857.826+31.8
- AA-Omniscience · AccuracyMuse Spark 1.1 by 21.35230.8+21.3
Images and chartsMuse Spark 1.1
- LMArena · VisionMuse Spark 1.1 by 30 rating points12941264+30 rating
Following instructionsMuse Spark 1.1
- Multi-ChallengeMuse Spark 1.1 by 7.775.367.6+7.7
Other results6 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.
- AA-OmniscienceMuse Spark 1.1 by 58.828.1-30.8+58.8
- ToolathlonMuse Spark 1.1 by 37.375.638.3+37.3
- Toolathlon VerifiedMuse Spark 1.1 by 34.975.640.7+34.9
- Artificial Analysis Coding IndexMuse Spark 1.1 by 23.171.348.2+23.1
- AA Agentic IndexMuse Spark 1.1 by 16.927.510.6+16.9
- AA IntelligenceMuse Spark 1.1 by 15.333.718.4+15.3
Questions people ask
Which is better, Muse Spark 1.1 or Qwen3.5 397B A17B?
Muse Spark 1.1 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and following instructions. Qwen3.5 397B A17B wins none, but costs 24% less. They are level on long documents.
Which is better for coding?
Muse Spark 1.1. It wins 4 of the 4 coding tests both models report; Qwen3.5 397B A17B wins none.
Which is cheaper?
Muse Spark 1.1 costs $1.25 per million input tokens and $4.25 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 24% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.