Model comparison
DeepSeek-V2.5 (Sep 2024) vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 37.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and GLM-5V-Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5V-Turbo leads 62.6 to 50.0.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 37.0 | 43.1 |
| Released | 2024-09-06 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $4 |
| Results tracked | 22 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1310 | 1467 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1443 |
Math GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1289 | 1440 |
Knowledge GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1266 | 1451 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1273 | 1420 |
| LMArena Chinese | 1317 | 1488 |
| LMArena French | 1288 | 1443 |
| LMArena German | 1258 | 1422 |
| LMArena Korean | 1209 | 1399 |
| LMArena Russian | 1289 | 1432 |
| LMArena Spanish | 1248 | 1446 |
| LMArena Japanese | 1228 | — |
Instruction Following GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1280 | 1422 |
Long Context GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1301 | 1439 |
Writing & Preference GLM-5V-Turbo leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1294 | 1437 |
| LMArena Creative Writing | 1285 | 1414 |
| LMArena Multi-Turn | 1297 | 1432 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 41.8 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GLM-5V-Turbo share?
16 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GLM-5V-Turbo has 19.