Model comparison
DeepSeek V4 Flash vs Qwen3-4B
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 31.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 3 categories and Qwen3-4B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for DeepSeek V4 Flash and 52.2% for Qwen3-4B.
Side by side
| DeepSeek V4 Flash | Qwen3-4B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 53.6 | 31.9 |
| Released | 2026-04-24 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek V4 Flash: 47.9 (#59), Qwen3-4B: —
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| LMArena Coding | 1457 | — |
| ALE-Bench | 1,306 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Flash: —, Qwen3-4B: 27.6 (#100)
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Qwen3-4B: 19.2 (#268)
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 33% | 4% |
| 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% | — |
| LMArena Hard Prompts | 1444 | — |
| 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), Qwen3-4B: 29.7 (#240)
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | 76.5% | 38.5% |
| OTIS Mock AIME 2024-2025 | 94.4% | 52.2% |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| ProofBench | 56% | — |
| LMArena Math | 1427 | — |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Qwen3-4B: 33.0 (#208)
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 91% | 52.3% |
| SimpleQA Verified | 33.6% | — |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1441 | — |
Multilingual Not comparable
DeepSeek V4 Flash: 53.0 (#72), Qwen3-4B: —
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1468 | — |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Not comparable
DeepSeek V4 Flash: 74.9 (#81), Qwen3-4B: —
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1421 | — |
Long Context Not comparable
DeepSeek V4 Flash: 43.8 (#85), Qwen3-4B: —
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference Not comparable
DeepSeek V4 Flash: 63.8 (#61), Qwen3-4B: —
| Benchmark | DeepSeek V4 Flash | Qwen3-4B |
|---|---|---|
| LMArena Text | 1432 | — |
| LMArena Creative Writing | 1403 | — |
| EQ-Bench Creative Writing | 1559 | — |
| LMArena Multi-Turn | 1449 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Qwen3-4B?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 31.9 on the Noometry Index.
How many benchmarks do DeepSeek V4 Flash and Qwen3-4B share?
4 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Qwen3-4B has 6.