Model comparison
DeepSeek V4 Pro vs GLM-5V-Turbo
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 43.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and GLM-5V-Turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.6 to 36.6.
- DeepSeek V4 Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 200K.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | GLM-5V-Turbo | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 54.2 | 43.1 |
| Released | 2026-04-24 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 200K |
| Max output | 393K | 131K |
| Input $ / M tokens | $0.43 | $1.20 |
| Output $ / M tokens | $0.87 | $4 |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.2 (#31), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena WebDev | 1582 | 1400 |
| LMArena Coding | 1470 | 1467 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.7 (#54), GLM-5V-Turbo: —
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.4 (#22), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1443 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.39 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.6 (#24), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1455 | 1440 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#28), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1463 | 1451 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multimodal Not comparable
DeepSeek V4 Pro: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.5 (#44), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1438 | 1420 |
| LMArena Chinese | 1486 | 1488 |
| LMArena French | 1473 | 1443 |
| LMArena German | 1458 | 1422 |
| LMArena Korean | 1452 | 1399 |
| LMArena Russian | 1452 | 1432 |
| LMArena Spanish | 1457 | 1446 |
| LMArena Japanese | 1448 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.3 (#44), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1448 | 1422 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#49), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1459 | 1439 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.6 (#45), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | DeepSeek V4 Pro | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1451 | 1437 |
| LMArena Creative Writing | 1446 | 1414 |
| LMArena Multi-Turn | 1467 | 1432 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than GLM-5V-Turbo?
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 43.1 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or GLM-5V-Turbo?
DeepSeek V4 Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is DeepSeek V4 Pro or GLM-5V-Turbo better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 200K.
How many benchmarks do DeepSeek V4 Pro and GLM-5V-Turbo share?
17 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and GLM-5V-Turbo has 19.