Model comparison
DeepSeek-R1 vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 42.0 on the Noometry Index. DeepSeek-R1 costs 2.1× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. DeepSeek-R1 scores higher in 4 categories and GLM-5V-Turbo in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5V-Turbo leads 28.5 to 18.7.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GLM-5V-Turbo accepts more context: 200K tokens versus 164K.
Side by side
| DeepSeek-R1 | GLM-5V-Turbo | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 42.0 | 43.1 |
| Released | 2025-01-20 | 2026-04-01 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 200K |
| Max output | 64K | 131K |
| Input $ / M tokens | $0.50 | $1.20 |
| Output $ / M tokens | $2.15 | $4 |
| Results tracked | 52 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 45.9 (#63), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1427 | 1467 |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1400 |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.4 (#68), GLM-5V-Turbo: —
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning GLM-5V-Turbo leads
DeepSeek-R1: 18.7 (#253), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1443 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.3 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 42.0 (#70), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1401 | 1440 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.3 (#81), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1394 | 1451 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual Too close to call
DeepSeek-R1: 52.6 (#80), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1412 | 1420 |
| LMArena Chinese | 1443 | 1488 |
| LMArena French | 1415 | 1443 |
| LMArena German | 1405 | 1422 |
| LMArena Korean | 1359 | 1399 |
| LMArena Russian | 1423 | 1432 |
| LMArena Spanish | 1410 | 1446 |
| LMArena Japanese | 1394 | — |
Instruction Following GLM-5V-Turbo leads
DeepSeek-R1: 72.2 (#138), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1382 | 1422 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1391 | 1439 |
| Fiction.LiveBench | 75% | — |
Writing & Preference GLM-5V-Turbo leads
DeepSeek-R1: 61.5 (#84), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | DeepSeek-R1 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1428 | 1437 |
| LMArena Creative Writing | 1406 | 1414 |
| LMArena Multi-Turn | 1404 | 1432 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 42.0 on the Noometry Index. DeepSeek-R1 costs 2.1× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or GLM-5V-Turbo?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is DeepSeek-R1 or GLM-5V-Turbo better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 41.8 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-R1 and GLM-5V-Turbo share?
16 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and GLM-5V-Turbo has 19.