BenchLeader

GLM-5 vs Muse Spark 1.3

Verdict
  • Muse Spark 1.3 leads on quality: 68.3 vs 59.2.
  • GLM-5 is stronger in agents & tools, coding, human preference, instruction following, maths, reasoning.
  • Muse Spark 1.3 is stronger in composite, knowledge, long context.
  • GLM-5 is 1.3× cheaper ($1.55 vs $2.00 per 1M blended).
  • Muse Spark 1.3 streams 3.0× faster (241 vs 81 tokens per second).
MetricGLM-5Muse Spark 1.3
BenchLeader Index59.268.3
Agents & tools score56.9
Coding score52.9
Composite score64.590.3
Human preference score65.4
Instruction following score71.0
Knowledge score64.579.1
Long context score64.468.2
Maths score53.2
Reasoning score51.5
Blended price $/M$1.55$2.00
Output speed81 tok/s241 tok/s
Time to first answer40.0 s30.5 s
Context window205k1.0M
GPQA Diamond87.8%
OTIS Mock AIME80.0%
SWE-bench Verified (Epoch)72.1%
Terminal-Bench52.4%
SimpleBench53.2%
WeirdML48.2%
APEX-Agents17.2%
Epoch Capabilities Index145.8
LMArena Text1458
LMArena Hard Prompts1478
LMArena Coding1498
LMArena WebDev1436
AA Intelligence Index27.948.2
IFBench72.3%
AA-LCR75.7%83.0%
AA-Omniscience0.325
Terminal-Bench Hard43.2%
GPQA Diamond (AA)82.0%93.5%
Humanity's Last Exam (AA)29.3%48.7%
SciCode (AA)58.8%
τ²-Bench Telecom (AA)98.3%
AIME 202696.7%
HMMT February 202686.4%
MathArena Apex10.9%
PRBench Finance59.5%
PRBench Legal61.6%
Kagi LLM Benchmark51.7%
ARC-AGI-144.7%
ARC-AGI-24.9%

Data as of 2026-09-14. Best configuration of each model; every score links to its source on the model pages.

GLM-5 vs Muse Spark 1.3: questions

Is GLM-5 better than Muse Spark 1.3?
Muse Spark 1.3 leads on quality: 68.3 vs 59.2. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 is ahead overall as of 2026-09-14, but check the category scores for your use.
Which is cheaper, GLM-5 or Muse Spark 1.3?
GLM-5 is cheaper: $1.55 against $2.00 per million tokens, blended at three input tokens per output token.
Which is faster, GLM-5 or Muse Spark 1.3?
Muse Spark 1.3 streams faster: 241 against 81 output tokens per second.
Which has the larger context window?
Muse Spark 1.3 accepts more context: 1.0M against 205k tokens.