Model comparison
DeepSeek V4 Pro vs Hunyuan Vision 1.5
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 43.1 on the Noometry Index.
Last verified . 8 shared benchmarks.
DeepSeek
TencentSummary
- They share 8 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 6 categories and Hunyuan Vision 1.5 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 28.9.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Hunyuan Vision 1.5 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 54.3 | 43.1 |
| 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 | 9 |
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), Hunyuan Vision 1.5: 41.8 (#119)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Coding | 1470 | 1418 |
| 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), Hunyuan Vision 1.5: —
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Hunyuan Vision 1.5: 28.9 (#97)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1416 |
| 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 Not comparable
DeepSeek V4 Pro: 64.8 (#30), Hunyuan Vision 1.5: —
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| 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% | — |
| LMArena Math | 1455 | — |
Knowledge Not comparable
DeepSeek V4 Pro: 59.5 (#31), Hunyuan Vision 1.5: —
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
Multimodal Not comparable
DeepSeek V4 Pro: —, Hunyuan Vision 1.5: 35.7 (#84)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Vision | — | 1180 |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Hunyuan Vision 1.5: 50.3 (#125)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Non-English | 1439 | 1382 |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Hunyuan Vision 1.5: 73.7 (#117)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Instruction Following | 1448 | 1397 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Hunyuan Vision 1.5: 42.9 (#115)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Longer Query | 1458 | 1404 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Hunyuan Vision 1.5: 60.1 (#100)
| Benchmark | DeepSeek V4 Pro | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Text | 1451 | 1405 |
| LMArena Creative Writing | 1446 | 1388 |
| LMArena Multi-Turn | 1467 | 1422 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Hunyuan Vision 1.5?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 43.1 on the Noometry Index.
Is DeepSeek V4 Pro or Hunyuan Vision 1.5 better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 41.8 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Hunyuan Vision 1.5 share?
8 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Hunyuan Vision 1.5 has 9.