Model comparison
DeepSeek LLM 67B vs GLM-4.6V
GLM-4.6V is the stronger model overall, scoring 41.3 to 24.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-4.6V in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6V leads 38.0 to 7.0.
Side by side
| DeepSeek LLM 67B | GLM-4.6V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 24.9 | 41.3 |
| Released | 2023-11-29 | 2025-12-08 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 15 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
DeepSeek LLM 67B: 31.9 (#278), GLM-4.6V: 40.9 (#128)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1096 | 1390 |
Reasoning GLM-4.6V leads
DeepSeek LLM 67B: 16.5 (#304), GLM-4.6V: 27.6 (#115)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1368 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Not comparable
DeepSeek LLM 67B: 8.7 (#324), GLM-4.6V: —
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge GLM-4.6V leads
DeepSeek LLM 67B: 7.0 (#313), GLM-4.6V: 38.0 (#149)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1371 |
Multimodal Not comparable
DeepSeek LLM 67B: —, GLM-4.6V: 34.8 (#90)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
Multilingual GLM-4.6V leads
DeepSeek LLM 67B: 29.4 (#267), GLM-4.6V: 48.6 (#141)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1073 | 1359 |
| LMArena Chinese | 1132 | 1425 |
| LMArena Russian | — | 1340 |
Instruction Following GLM-4.6V leads
DeepSeek LLM 67B: 55.4 (#277), GLM-4.6V: 71.4 (#151)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1079 | 1352 |
Long Context GLM-4.6V leads
DeepSeek LLM 67B: 33.1 (#265), GLM-4.6V: 41.3 (#143)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1092 | 1358 |
Writing & Preference GLM-4.6V leads
DeepSeek LLM 67B: 31.6 (#282), GLM-4.6V: 56.6 (#137)
| Benchmark | DeepSeek LLM 67B | GLM-4.6V |
|---|---|---|
| LMArena Text | 1105 | 1377 |
| LMArena Creative Writing | 1067 | 1347 |
| LMArena Multi-Turn | 1082 | 1360 |
Frequently asked questions
Is DeepSeek LLM 67B better than GLM-4.6V?
GLM-4.6V is the stronger model overall, scoring 41.3 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or GLM-4.6V better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.9 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GLM-4.6V share?
9 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-4.6V has 12.