Model comparison
DeepSeek-V3.1-Terminus vs GLM-4.6V
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 5 categories and GLM-4.6V in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 56.8.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.
Side by side
| DeepSeek-V3.1-Terminus | GLM-4.6V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 42.6 | 40.9 |
| Released | 2025-09-22 | 2025-12-08 |
| Weights | Open | Open |
| Context window | 164K | 128K |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $1 | $0.90 |
| Results tracked | 16 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), GLM-4.6V: 40.2 (#128)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1426 | 1390 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning Too close to call
DeepSeek-V3.1-Terminus: 25.7 (#126), GLM-4.6V: 26.5 (#117)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1368 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Not comparable
DeepSeek-V3.1-Terminus: 35.7 (#138), GLM-4.6V: —
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Math | 1402 | — |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, GLM-4.6V: 37.4 (#148)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Expert | — | 1372 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, GLM-4.6V: 34.2 (#83)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), GLM-4.6V: 48.8 (#135)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1407 | 1359 |
| LMArena Russian | 1434 | 1341 |
| LMArena Chinese | — | 1426 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), GLM-4.6V: 71.6 (#145)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1406 | 1351 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), GLM-4.6V: 41.3 (#138)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1426 | 1358 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), GLM-4.6V: 56.8 (#132)
| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.6V |
|---|---|---|
| LMArena Text | 1420 | 1377 |
| LMArena Creative Writing | 1404 | 1347 |
| LMArena Multi-Turn | 1411 | 1359 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than GLM-4.6V?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.9 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or GLM-4.6V?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or GLM-4.6V better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 40.2 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1-Terminus and GLM-4.6V share?
9 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GLM-4.6V has 12.