Model comparison
DeepSeek-V2.5 (Sep 2024) vs GLM-4.5
GLM-4.5 is the stronger model overall, scoring 42.0 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and GLM-4.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.5 leads 52.8 to 42.5.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GLM-4.5 | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 37.6 | 42.0 |
| Released | 2024-09-06 | 2025-07-27 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), GLM-4.5: 41.4 (#125)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Coding | 1309 | 1434 |
| SWE-bench Verified (bash only) | — | 54.2% |
| Aider Polyglot | 17.8% | — |
| WeirdML | — | 40.6% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 344.82 |
| AlgoTune | — | 1.52 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), GLM-4.5: 28.6 (#100)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1429 |
| Kagi LLM Benchmark | — | 57.9% |
Math GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), GLM-4.5: 39.0 (#116)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Math | 1288 | 1427 |
Knowledge GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), GLM-4.5: 35.9 (#179)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Expert | 1266 | 1433 |
| Humanity's Last Exam | — | 8.3% |
| Confabulations | — | 11.3% |
Multilingual GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), GLM-4.5: 52.8 (#77)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Non-English | 1273 | 1417 |
| LMArena Chinese | 1318 | 1465 |
| LMArena French | 1289 | 1418 |
| LMArena German | 1258 | 1407 |
| LMArena Japanese | 1228 | 1415 |
| LMArena Korean | 1209 | 1380 |
| LMArena Russian | 1289 | 1414 |
| LMArena Spanish | 1248 | 1454 |
Instruction Following GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), GLM-4.5: 74.1 (#104)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1404 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), GLM-4.5: 38.2 (#201)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Longer Query | 1301 | 1412 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference GLM-4.5 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), GLM-4.5: 57.5 (#127)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.5 |
|---|---|---|
| LMArena Text | 1294 | 1430 |
| LMArena Creative Writing | 1285 | 1395 |
| LMArena Multi-Turn | 1297 | 1415 |
| Short-Story Creative Writing | — | 73.4% |
| EQ-Bench Creative Writing | — | 1343 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GLM-4.5?
GLM-4.5 is the stronger model overall, scoring 42.0 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GLM-4.5 better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GLM-4.5 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GLM-4.5 has 27.