Model comparison
DeepSeek-V2.5 (Sep 2024) vs GLM-4.7-Flash
GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 37.6 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 2 categories and GLM-4.7-Flash in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-4.7-Flash leads 40.6 to 31.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 37.6 | 38.8 |
| Released | 2024-09-06 | 2026-01-19 |
| Weights | Open | Open |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.06 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7-Flash leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), GLM-4.7-Flash: 40.6 (#135)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Coding | 1309 | 1383 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), GLM-4.7-Flash: 20.9 (#229)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1356 |
| Chess Puzzles | — | 0% |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), GLM-4.7-Flash: 36.1 (#173)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Math | 1288 | 1355 |
| OTIS Mock AIME 2024-2025 | — | 58.3% |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), GLM-4.7-Flash: 35.5 (#184)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Expert | 1266 | 1357 |
| GPQA Diamond | — | 60.5% |
| Vectara Hallucination Rate | — | 9.3% |
Multilingual GLM-4.7-Flash leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), GLM-4.7-Flash: 46.5 (#158)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1330 |
| LMArena Chinese | 1318 | 1403 |
| LMArena French | 1289 | 1332 |
| LMArena German | 1258 | 1337 |
| LMArena Korean | 1209 | 1283 |
| LMArena Russian | 1289 | 1332 |
| LMArena Spanish | 1248 | 1350 |
| LMArena Japanese | 1228 | — |
Instruction Following GLM-4.7-Flash leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), GLM-4.7-Flash: 70.1 (#167)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1327 |
Long Context GLM-4.7-Flash leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), GLM-4.7-Flash: 40.9 (#148)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1345 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), GLM-4.7-Flash: 47.4 (#210)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GLM-4.7-Flash |
|---|---|---|
| LMArena Text | 1294 | 1351 |
| LMArena Creative Writing | 1285 | 1297 |
| LMArena Multi-Turn | 1297 | 1342 |
| EQ-Bench Creative Writing | — | 1125 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GLM-4.7-Flash?
GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GLM-4.7-Flash better for coding?
GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GLM-4.7-Flash share?
16 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GLM-4.7-Flash has 21.