Model comparison
DeepSeek V4 Pro vs Hunyuan Large Vision
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 37.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
TencentSummary
- They share 12 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Hunyuan Large Vision in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.4 to 23.8.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Hunyuan Large Vision | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 54.2 | 37.0 |
| Released | 2026-04-24 | — |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 48 | 13 |
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), Hunyuan Large Vision: 37.6 (#176)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Coding | 1470 | 1307 |
| 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: 32.7 (#54), Hunyuan Large Vision: —
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.4 (#22), Hunyuan Large Vision: 23.8 (#160)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1257 |
| 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), Hunyuan Large Vision: 32.8 (#184)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Math | 1455 | 1269 |
| 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), Hunyuan Large Vision: 33.7 (#191)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Expert | 1463 | 1250 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multimodal Not comparable
DeepSeek V4 Pro: —, Hunyuan Large Vision: 35.1 (#79)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Vision | — | 1180 |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.5 (#44), Hunyuan Large Vision: 40.1 (#216)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Non-English | 1438 | 1236 |
| LMArena Chinese | 1486 | 1289 |
| LMArena Russian | 1452 | 1243 |
| LMArena French | 1473 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1448 | — |
| LMArena Korean | 1452 | — |
| LMArena Spanish | 1457 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.3 (#44), Hunyuan Large Vision: 66.0 (#210)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Instruction Following | 1448 | 1250 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#49), Hunyuan Large Vision: 38.8 (#184)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Longer Query | 1459 | 1279 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.6 (#45), Hunyuan Large Vision: 46.7 (#211)
| Benchmark | DeepSeek V4 Pro | Hunyuan Large Vision |
|---|---|---|
| LMArena Text | 1451 | 1263 |
| LMArena Creative Writing | 1446 | 1250 |
| LMArena Multi-Turn | 1467 | 1253 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Hunyuan Large Vision?
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 37.0 on the Noometry Index.
Is DeepSeek V4 Pro or Hunyuan Large Vision better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 37.6 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Hunyuan Large Vision share?
12 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Hunyuan Large Vision has 13.