Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen2.5 32B Instruct
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 3 categories and Qwen2.5 32B Instruct in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 33.3 to 15.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.0 | 29.7 |
| Released | 2024-09-06 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 22 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Qwen2.5 32B Instruct: 38.1 (#165)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.6% | 45% |
| BigCodeBench Complete | 53.2% | 52.3% |
| Aider Polyglot | 17.8% | — |
| LMArena Coding | 1310 | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Qwen2.5 32B Instruct: 18.5 (#262)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1289 | — |
| Epoch Capabilities Index | — | 128.52 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Qwen2.5 32B Instruct: 15.3 (#289)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| LMArena Math | 1289 | — |
| MATH Level 5 | — | 56.1% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Qwen2.5 32B Instruct: 24.9 (#259)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| LMArena Expert | 1266 | — |
Multilingual Not comparable
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1317 | — |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Not comparable
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1280 | — |
Long Context Not comparable
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1301 | — |
Writing & Preference Not comparable
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| LMArena Multi-Turn | 1297 | — |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen2.5 32B Instruct?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 29.7 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen2.5 32B Instruct better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.1 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen2.5 32B Instruct share?
2 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen2.5 32B Instruct has 7.