Llama 3.1 Instruct 405B vs Muse Spark 1.1
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Coding · Agents · Reasoning · Facts · Long documents
Muse Spark 1.1 is the stronger all-rounder.
Scores updated · 13 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- ReasoningHard problems that need careful thinking03Muse Spark 1.13 of 3 tests
- CodingWriting and fixing software02Muse Spark 1.12 of 2 tests
- FactsGetting facts right instead of making them up02Muse Spark 1.12 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Muse Spark 1.11 of 1 test
- Long documentsFinding answers in very long texts01Muse Spark 1.11 of 1 test
Agents and long documents 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.
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
- Reasons across sets of long documentsAA-LCR+52.4points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+50.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+42.2points ahead
Where Llama 3.1 Instruct 405B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMuse Spark 1.1
- SWE-bench ProMuse Spark 1.1 by 50.311.261.5+50.3
- SciCodeMuse Spark 1.1 by 28.929.958.8+28.9
ReasoningMuse Spark 1.1
- Humanity's Last ExamMuse Spark 1.1 by 42.2446.2+42.2
- GPQA DiamondMuse Spark 1.1 by 38.351.589.8+38.3
- CritPtMuse Spark 1.1 by 15.1015.1+15.1
FactsMuse Spark 1.1
- AA-Omniscience · AccuracyMuse Spark 1.1 by 28.923.252+28.9
- AA-Omniscience · Non-hallucinationMuse Spark 1.1 by 2.447.650+2.4
Other results4 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.
- Artificial Analysis Coding IndexMuse Spark 1.1 by 56.814.571.3+56.8
- AA-OmniscienceMuse Spark 1.1 by 45.2-17.128.1+45.2
- AA IntelligenceMuse Spark 1.1 by 26.47.333.7+26.4
- AA Agentic IndexMuse Spark 1.1 by 21.26.327.5+21.2
Questions people ask
Which is better, Llama 3.1 Instruct 405B or Muse Spark 1.1?
Muse Spark 1.1 wins all five areas where both have results: coding, agents, reasoning, facts and long documents. Llama 3.1 Instruct 405B wins none.
Which is better for coding?
Muse Spark 1.1. It wins 2 of the 2 coding tests both models report; Llama 3.1 Instruct 405B wins none.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.