Model comparison
DeepSeek V4 Flash vs Qwen Max
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 34.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Flash leads 60.3 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for DeepSeek V4 Flash and 16.1% for Qwen Max.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 33K.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Flash | Qwen Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 53.6 | 34.7 |
| Released | 2026-04-24 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 1M | 33K |
| Max output | 393K | 8K |
| Input $ / M tokens | $0.15 | $1.60 |
| Output $ / M tokens | $0.60 | $6.40 |
| Results tracked | 41 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), Qwen Max: 30.7 (#292)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| LMArena Coding | 1457 | 1288 |
| FrontierCode | 18.8% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Qwen Max: 25.1 (#151)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1269 |
| 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 | 154.49 | — |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Qwen Max: 22.3 (#276)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 16.1% |
| LMArena Math | 1427 | 1275 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Qwen Max: 30.3 (#228)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| GPQA Diamond | 91% | 56.1% |
| LMArena Expert | 1441 | 1248 |
| SimpleQA Verified | 33.6% | — |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Qwen Max: 41.8 (#202)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| LMArena Non-English | 1420 | 1263 |
| LMArena Chinese | 1468 | 1254 |
| LMArena French | 1439 | 1330 |
| LMArena German | 1418 | 1254 |
| LMArena Japanese | 1406 | 1205 |
| LMArena Korean | 1384 | 1142 |
| LMArena Russian | 1428 | 1274 |
| LMArena Spanish | 1436 | 1290 |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Qwen Max: 66.5 (#208)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1421 | 1262 |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#85), Qwen Max: 39.4 (#180)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1434 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Qwen Max: 47.8 (#205)
| Benchmark | DeepSeek V4 Flash | Qwen Max |
|---|---|---|
| LMArena Text | 1432 | 1282 |
| LMArena Creative Writing | 1403 | 1248 |
| LMArena Multi-Turn | 1449 | 1277 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Qwen Max?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 34.7 on the Noometry Index.
Which is cheaper, DeepSeek V4 Flash or Qwen Max?
DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is DeepSeek V4 Flash or Qwen Max better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Flash does, with 1M tokens against 33K.
How many benchmarks do DeepSeek V4 Flash and Qwen Max share?
19 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Qwen Max has 23.