Model comparison
DeepSeek-V3.1 vs GLM-4.6V
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 41.3 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 5 categories and GLM-4.6V in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 38.0.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.30 / $0.90 for GLM-4.6V.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.
Side by side
| DeepSeek-V3.1 | GLM-4.6V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 42.8 | 41.3 |
| Released | 2025-08-21 | 2025-12-08 |
| Weights | Open | Open |
| Context window | 164K | 128K |
| Max output | 8K | 33K |
| Input $ / M tokens | $0.25 | $0.30 |
| Output $ / M tokens | $0.95 | $0.90 |
| Results tracked | 27 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1: 40.3 (#144), GLM-4.6V: 40.9 (#128)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1417 | 1390 |
| WeirdML | 38.4% | — |
Reasoning Too close to call
DeepSeek-V3.1: 27.9 (#110), GLM-4.6V: 27.6 (#115)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1368 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Not comparable
DeepSeek-V3.1: 38.9 (#122), GLM-4.6V: —
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Math | 1420 | — |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), GLM-4.6V: 38.0 (#149)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Expert | 1405 | 1371 |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
DeepSeek-V3.1: —, GLM-4.6V: 34.8 (#90)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), GLM-4.6V: 48.6 (#141)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1400 | 1359 |
| LMArena Chinese | 1469 | 1425 |
| LMArena Russian | 1405 | 1340 |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), GLM-4.6V: 71.4 (#151)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1400 | 1352 |
Long Context GLM-4.6V leads
DeepSeek-V3.1: 36.3 (#232), GLM-4.6V: 41.3 (#143)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1422 | 1358 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), GLM-4.6V: 56.6 (#137)
| Benchmark | DeepSeek-V3.1 | GLM-4.6V |
|---|---|---|
| LMArena Text | 1420 | 1377 |
| LMArena Creative Writing | 1401 | 1347 |
| LMArena Multi-Turn | 1408 | 1360 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than GLM-4.6V?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 41.3 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or GLM-4.6V?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GLM-4.6V lists at $0.30 and $0.90.
Is DeepSeek-V3.1 or GLM-4.6V better for coding?
They score almost the same on coding (40.3 vs 40.9); test both on your own repository before choosing.
Which has the bigger context window?
DeepSeek-V3.1 does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1 and GLM-4.6V share?
11 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GLM-4.6V has 12.