Model comparison
DeepSeek V4 Flash vs Hunyuan Large 2025 02 10
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 38.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
TencentSummary
- They share 12 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Hunyuan Large 2025 02 10 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 24.5.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Flash | Hunyuan Large 2025 02 10 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 53.6 | 38.0 |
| Released | 2026-04-24 | — |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.6 (#56), Hunyuan Large 2025 02 10: 37.6 (#177)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Coding | 1457 | 1307 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1581 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#25), Hunyuan Large 2025 02 10: 24.5 (#147)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1286 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.51 | — |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.0 (#31), Hunyuan Large 2025 02 10: 33.1 (#178)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Math | 1427 | 1281 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.5 (#43), Hunyuan Large 2025 02 10: 34.5 (#188)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Expert | 1441 | 1276 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.2 (#71), Hunyuan Large 2025 02 10: 42.1 (#195)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Non-English | 1420 | 1265 |
| LMArena Chinese | 1467 | 1346 |
| LMArena Russian | 1428 | 1266 |
| LMArena French | 1438 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1383 | — |
| LMArena Spanish | 1437 | — |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 75.1 (#76), Hunyuan Large 2025 02 10: 67.6 (#192)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1277 |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#81), Hunyuan Large 2025 02 10: 40.8 (#144)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Longer Query | 1435 | 1342 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 64.0 (#59), Hunyuan Large 2025 02 10: 48.9 (#191)
| Benchmark | DeepSeek V4 Flash | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Text | 1432 | 1288 |
| LMArena Creative Writing | 1403 | 1264 |
| LMArena Multi-Turn | 1449 | 1284 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Hunyuan Large 2025 02 10?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 38.0 on the Noometry Index.
Is DeepSeek V4 Flash or Hunyuan Large 2025 02 10 better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 37.6 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Hunyuan Large 2025 02 10 share?
12 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Hunyuan Large 2025 02 10 has 12.