Model comparison
DeepSeek V4 Pro vs Qwen2.5 Plus 1127
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 38.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Qwen2.5 Plus 1127 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 25.9.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 54.3 | 38.8 |
| Released | 2026-04-24 | — |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1470 | 1314 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Qwen2.5 Plus 1127: —
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1299 |
| 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 | 155.31 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1455 | 1298 |
| 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 (#31), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1464 | 1289 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1439 | 1265 |
| LMArena Chinese | 1486 | 1314 |
| LMArena German | 1458 | 1231 |
| LMArena Japanese | 1445 | 1207 |
| LMArena Russian | 1453 | 1271 |
| LMArena French | 1472 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1448 | 1275 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1458 | 1292 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1451 | 1299 |
| LMArena Creative Writing | 1446 | 1262 |
| LMArena Multi-Turn | 1467 | 1299 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Qwen2.5 Plus 1127?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 38.8 on the Noometry Index.
Is DeepSeek V4 Pro or Qwen2.5 Plus 1127 better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 38.5 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen2.5 Plus 1127 has 14.