Model comparison
DeepSeek-V3 vs Qwen3.7 Flash
DeepSeek-V3 and Qwen3.7 Flash score almost the same on the Noometry Index (39.5 vs 39.9), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. DeepSeek-V3 scores higher in 0 categories and Qwen3.7 Flash in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Flash leads 48.9 to 37.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for DeepSeek-V3 and 86.7% for Qwen3.7 Flash.
- Qwen3.7 Flash is cheaper at $0.03 / $0.13 per million input/output tokens, against $0.24 / $0.90 for DeepSeek-V3.
- Qwen3.7 Flash accepts more context: 1M tokens versus 164K.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | Qwen3.7 Flash | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 39.5 | 39.9 |
| Released | 2024-12-26 | 2026-07-15 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 164K | 131K |
| Input $ / M tokens | $0.24 | $0.03 |
| Output $ / M tokens | $0.90 | $0.13 |
| Results tracked | 60 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V3: 42.3 (#106), Qwen3.7 Flash: —
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| Aider Polyglot | 55.1% | — |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| LMArena Coding | 1368 | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Qwen3.7 Flash: —
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| METR Time Horizons | 49.6% | — |
Reasoning Qwen3.7 Flash leads
DeepSeek-V3: 20.5 (#236), Qwen3.7 Flash: 28.2 (#108)
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| Epoch Capabilities Index | 135.94 | 144.64 |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 43.8% |
| CritPt | 0% | — |
| Chess Puzzles | — | 23% |
| LiveBench Reasoning | 65.8% | — |
| LMArena Hard Prompts | 1365 | — |
| Mystery Game Puzzles | — | 15% |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math Qwen3.7 Flash leads
DeepSeek-V3: 32.1 (#219), Qwen3.7 Flash: 38.3 (#140)
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 86.7% |
| FrontierMath (Tiers 1-3) | — | 19.3% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| LMArena Math | 1373 | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Qwen3.7 Flash leads
DeepSeek-V3: 37.5 (#155), Qwen3.7 Flash: 48.9 (#75)
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| GPQA Diamond | 67.6% | 82.3% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| LMArena Expert | 1351 | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual Not comparable
DeepSeek-V3: 48.5 (#143), Qwen3.7 Flash: —
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| LMArena Non-English | 1358 | — |
| LMArena Chinese | 1391 | — |
| LMArena French | 1385 | — |
| LMArena German | 1374 | — |
| LMArena Japanese | 1333 | — |
| LMArena Korean | 1319 | — |
| LMArena Russian | 1373 | — |
| LMArena Spanish | 1358 | — |
Instruction Following Not comparable
DeepSeek-V3: 72.8 (#130), Qwen3.7 Flash: —
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
| LMArena Instruction Following | 1345 | — |
Long Context Not comparable
DeepSeek-V3: 34.0 (#253), Qwen3.7 Flash: —
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| Fiction.LiveBench | 50% | — |
| LMArena Longer Query | 1352 | — |
Writing & Preference Not comparable
DeepSeek-V3: 57.4 (#130), Qwen3.7 Flash: —
| Benchmark | DeepSeek-V3 | Qwen3.7 Flash |
|---|---|---|
| LMArena Text | 1375 | — |
| LMArena Creative Writing | 1364 | — |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LMArena Multi-Turn | 1389 | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Qwen3.7 Flash?
DeepSeek-V3 and Qwen3.7 Flash score almost the same on the Noometry Index (39.5 vs 39.9), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3 or Qwen3.7 Flash?
Qwen3.7 Flash is cheaper. It lists at $0.03 per million input tokens and $0.13 per million output tokens; DeepSeek-V3 lists at $0.24 and $0.90.
Which has the bigger context window?
Qwen3.7 Flash does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3 and Qwen3.7 Flash share?
3 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Qwen3.7 Flash has 7.