Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 34.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 42.5 |
| Released | 2024-09-06 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1309 | 1412 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1244 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 221.8 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Qwen3.5-Flash: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1403 |
| Chess Puzzles | — | 21% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
| Epoch Capabilities Index | — | 143.98 |
Math Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Math | 1288 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Expert | 1266 | 1407 |
| GPQA Diamond | — | 82.3% |
| SimpleQA Verified | — | 20.3% |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1385 |
| LMArena Chinese | 1318 | 1446 |
| LMArena French | 1289 | 1412 |
| LMArena German | 1258 | 1390 |
| LMArena Japanese | 1228 | 1368 |
| LMArena Korean | 1209 | 1344 |
| LMArena Russian | 1289 | 1379 |
| LMArena Spanish | 1248 | 1400 |
Instruction Following Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1374 |
Long Context Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1392 |
Writing & Preference Qwen3.5-Flash leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1294 | 1397 |
| LMArena Creative Writing | 1285 | 1343 |
| LMArena Multi-Turn | 1297 | 1393 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen3.5-Flash better for coding?
Qwen3.5-Flash scores higher on coding benchmarks: 34.2 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3.5-Flash share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3.5-Flash has 32.