Model comparison
DeepSeek-V3.1 vs GLM-5V-Turbo
DeepSeek-V3.1 and GLM-5V-Turbo score almost the same on the Noometry Index (42.8 vs 43.8), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and GLM-5V-Turbo in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where GLM-5V-Turbo leads 44.0 to 36.3.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GLM-5V-Turbo accepts more context: 200K tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | GLM-5V-Turbo | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 42.8 | 43.8 |
| Released | 2025-08-21 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $1.20 |
| Output $ / M tokens | $0.95 | $4 |
| Results tracked | 27 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
DeepSeek-V3.1: 40.3 (#144), GLM-5V-Turbo: 42.1 (#111)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1417 | 1466 |
| LMArena WebDev | — | 1401 |
| WeirdML | 38.4% | — |
Reasoning GLM-5V-Turbo leads
DeepSeek-V3.1: 27.9 (#110), GLM-5V-Turbo: 29.7 (#89)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1443 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Too close to call
DeepSeek-V3.1: 38.9 (#122), GLM-5V-Turbo: 39.4 (#106)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1420 | 1441 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), GLM-5V-Turbo: 40.6 (#117)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1405 | 1452 |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
DeepSeek-V3.1: —, GLM-5V-Turbo: 40.9 (#42)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual GLM-5V-Turbo leads
DeepSeek-V3.1: 51.6 (#106), GLM-5V-Turbo: 53.0 (#73)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1400 | 1420 |
| LMArena Chinese | 1469 | 1488 |
| LMArena French | 1447 | 1444 |
| LMArena German | 1411 | 1423 |
| LMArena Korean | 1337 | 1396 |
| LMArena Russian | 1405 | 1431 |
| LMArena Spanish | 1431 | 1450 |
| LMArena Japanese | 1378 | — |
Instruction Following GLM-5V-Turbo leads
DeepSeek-V3.1: 73.9 (#110), GLM-5V-Turbo: 75.0 (#80)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1400 | 1423 |
Long Context GLM-5V-Turbo leads
DeepSeek-V3.1: 36.3 (#232), GLM-5V-Turbo: 44.0 (#80)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1422 | 1438 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference GLM-5V-Turbo leads
DeepSeek-V3.1: 60.3 (#98), GLM-5V-Turbo: 62.5 (#73)
| Benchmark | DeepSeek-V3.1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1420 | 1437 |
| LMArena Creative Writing | 1401 | 1416 |
| LMArena Multi-Turn | 1408 | 1432 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than GLM-5V-Turbo?
DeepSeek-V3.1 and GLM-5V-Turbo score almost the same on the Noometry Index (42.8 vs 43.8), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1 or GLM-5V-Turbo?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is DeepSeek-V3.1 or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 42.1 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5V-Turbo does, with 200K tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and GLM-5V-Turbo share?
16 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GLM-5V-Turbo has 19.