Model comparison
GLM-4.6V vs Sonar
GLM-4.6V is the stronger model overall, scoring 41.3 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in reasoning, where GLM-4.6V leads 27.6 to 21.1.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1 / $1 for Sonar.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6V | Sonar | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Perplexity |
| Noometry Index | 41.3 | 38.5 |
| Released | 2025-12-08 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.30 | $1 |
| Output $ / M tokens | $0.90 | $1 |
| Results tracked | 12 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
GLM-4.6V: 40.9 (#128), Sonar: 35.7 (#221)
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1390 | — |
Reasoning GLM-4.6V leads
GLM-4.6V: 27.6 (#115), Sonar: 21.1 (#227)
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1368 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Not comparable
GLM-4.6V: —, Sonar: 33.7 (#200)
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
Knowledge Not comparable
GLM-4.6V: 38.0 (#149), Sonar: —
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LMArena Expert | 1371 | — |
Multimodal Not comparable
GLM-4.6V: 34.8 (#90), Sonar: —
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LMArena Vision | 1164 | — |
Multilingual Not comparable
GLM-4.6V: 48.6 (#141), Sonar: —
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1340 | — |
Instruction Following Too close to call
GLM-4.6V: 71.4 (#151), Sonar: 71.4 (#150)
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1352 | — |
Long Context Not comparable
GLM-4.6V: 41.3 (#143), Sonar: —
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LMArena Longer Query | 1358 | — |
Writing & Preference GLM-4.6V leads
GLM-4.6V: 56.6 (#137), Sonar: 52.6 (#167)
| Benchmark | GLM-4.6V | Sonar |
|---|---|---|
| LMArena Text | 1377 | — |
| LMArena Creative Writing | 1347 | — |
| LMArena Multi-Turn | 1360 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is GLM-4.6V better than Sonar?
GLM-4.6V is the stronger model overall, scoring 41.3 to 38.5 on the Noometry Index.
Which is cheaper, GLM-4.6V or Sonar?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Sonar lists at $1 and $1.
Is GLM-4.6V or Sonar better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.9 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GLM-4.6V and Sonar share?
0 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Sonar has 7.