Model comparison
DeepSeek-V2.5 (Sep 2024) vs GLM-4.6V
GLM-4.6V is the stronger model overall, scoring 40.9 to 37.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and GLM-4.6V in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-4.6V leads 40.2 to 31.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GLM-4.6V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 37.0 | 40.9 |
| Released | 2024-09-06 | 2025-12-08 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 22 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), GLM-4.6V: 40.2 (#128)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1310 | 1390 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), GLM-4.6V: 26.5 (#117)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1368 |
Math Not comparable
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), GLM-4.6V: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Math | 1289 | — |
Knowledge GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), GLM-4.6V: 37.4 (#148)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Expert | 1266 | 1372 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, GLM-4.6V: 34.2 (#83)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
Multilingual GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), GLM-4.6V: 48.8 (#135)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1273 | 1359 |
| LMArena Chinese | 1317 | 1426 |
| LMArena Russian | 1289 | 1341 |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), GLM-4.6V: 71.6 (#145)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1280 | 1351 |
Long Context GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), GLM-4.6V: 41.3 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1301 | 1358 |
Writing & Preference GLM-4.6V leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), GLM-4.6V: 56.8 (#132)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.6V |
|---|---|---|
| LMArena Text | 1294 | 1377 |
| LMArena Creative Writing | 1285 | 1347 |
| LMArena Multi-Turn | 1297 | 1359 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GLM-4.6V?
GLM-4.6V is the stronger model overall, scoring 40.9 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GLM-4.6V better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.2 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GLM-4.6V share?
11 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GLM-4.6V has 12.